A shorter README, and a guide for everything else

• The README is now a short page for judges and first-time visitors: the online demo, where to look for each judging criterion, one incident end to end, what's interesting, what was measured, and the contest checklist, with the full video (3:04) linked at the top.
• Install, features and administration moved, word for word, into a new OcuTalon guide. The page's install, model-key and Telegram links, and the install script's failure help, now point to it.

Webhooks, on your own install

• An admin creates a webhook in Settings, under Channels, with a name and a secret. Any other system can then send it a JSON event with POST, with the secret in a header.
• OcuTalon answers at once, then decides on the event as untrusted content: it can lead to a notice or to your digest, and nothing in the event can approve, change or run anything. The decision shows on the History page, and the event and its decision in Visual Trace. The secret is kept only as a salted hash.
• Webhooks are off on the online demo, which has no public webhook address. Try it on your own install: More to try, Send an event through a webhook.

Your own mailbox, on your own install

• An admin connects a POP3 mailbox in Settings > Channels > Email. OcuTalon makes an attention decision on each email that arrives after that, sends the email to the model for it, and leaves your mail on the server.
• Email is read as untrusted content: nothing in an email can approve, change or run anything. The online demo keeps its simulated mailbox.

Queue backlogs between digests

• Ask OcuTalon in the chat to watch the queue backlogs, and every minute it reads the queues of each production it can read. When a queue holds more than 100 messages, or its oldest message has waited over 10 minutes (an admin can change both), OcuTalon decides once whether to tell you now, and again only after the queue has dropped below and backed up again.
• The check only reads, and a run that can't read a namespace shows Not checked, never Passed. Try it: More to try, Watch queue backlogs.

Partner notices say only how the incident ended

• When you ask OcuTalon to warn the partner, its own code now adds how the incident ended to the draft's facts, from the incident's records: for example "all 50 affected orders went through after the fix", or, after a reroute, that they "were resent by another route". When the records don't match one of those endings exactly, the notice doesn't say whether the orders went through.
• A notice for a resolved incident no longer says that work is still going on. On the online demo the simulated partner contact is now Orders Partner IT. Try it: after the guide's incident, More to try, Warn the partner.

A suspended item keeps its incident open

• On your own install, an incident whose fix suspended an item now stays open until you ask OcuTalon to resume the item, or dismiss the incident yourself, so you can still undo the suspend the governed way: an approval request with its own dry run.
• If you dismiss it while the item is still disabled, the next check reports the disabled item once, with the time of the suspend. Suspend and resume stay refused on the online demo, where every visitor shares the Orders production.

More to try

• The guide's More to try panel now has 16 items, 15 of them on the online demo.

For developers

• The evaluation can now measure the fixed rules alone, with no model and no key: eval/run.sh --rules-only, on the main set of cases and on a held-out set.

Requires the InterSystems IRIS for Health AI Hub Early Access image, build 154 or build 109. Upgrading from 1.0.7 keeps your conversations, reminders, watches, approval requests, settings, memories, documents and Telegram pairing. The online demo runs 1.0.8.

---

Online demo: https://demo.ocutalon.com · Guide: https://github.com/jbrandtmse/OcuTalon/blob/main/GUIDE.md · Open Exchange: https://openexchange.intersystems.com/package/OcuTalon

1.0.1

Added

• Online demo support (InterSystems DevCloud): the Dockerfile now defaults to the AI Hub build 154 image that DevCloud can pull, and sets the non-secret demo settings (SN_SIM_BASE_URL, SN_BACKGROUND_TASKS=1), so it runs with no .env. Local installs are unchanged: docker compose still builds on the image you load and retag.
• "Signal Noir at a glance" in the README: an infographic and a short text walkthrough of the six steps, from a failed Order to the partner's confirmation.
• Logo in the operator console's top bar and as its favicon.
• Developer Community article (English version), with code, console screens and the infographic.

Changed

• The README and the article link the repository by its new name, musketeers-br/signal-noir.

Notes

• No change to the Agent, the Validator or the API: the frozen reference run (agent-v5, gpt-4o-mini, rules-v2) still applies.
• The provider key is never set in the image. Without one, Cases go to review with a Dossier that says the provider is unavailable.

• Replaced the Python PEX name comparison operation with a Java PEX implementation.
• Added native Interoperability message tracing for AI model and tool calls.
• Updated package resources and installation setup for the Java operation and tracing components.

• Replaced the Python PEX query embedding operation with a Java PEX implementation using the pinned ONNX model.
• Added native Interoperability message tracing for AI model and tool calls.
• Updated package resources and installation setup for the Java operation and tracing components.

add Deployment version

Listing update: the video field now links the YouTube demo and the MP4 (the old field joined two URLs). The package code is unchanged from 0.1.9 on the community registry.

Shutter 1.4.4 lets anyone on the online demo play the scenarios, from their recordings.

• The public demo's account can press Run on Scenarios: every agent of its cases replays its recording, so no model is called and nothing counts against the demo's budget. The judges' runs stay live.
• A replayed run says so on its case, its agent runs and its banner. The single investigator, never recorded, is greyed out for it.
• Reset stays locked for the public account; the hourly reset cleans up after visitors.
• The docs name the two recovery paths and what each guarantees: a write through the receiver's API is verified at the receiver; an outage's resend through the engine is settled by the receiver's declared duplicate handling.
• A demo video: 13 minutes recorded live on the online demo, with captions, on YouTube and attached to the release as an MP4 that downloads without signing in.
• The README leads judges through the whole workflow, with links to the classes that carry it, and puts the measured results first: all twelve held-out cases rerun on 1.4.3, with no wrong write executed in any mode.
• The README says the judges share one account on the demo, and with it 2 USD of live runs an hour; when that is spent, the demo account still plays the scenarios from their recordings.

Documentation corrected since the release (no code change):

• S8's comparison names the one gate check it lifts, ENTRY_NOT_NAMED_WRITE, for a recorded scenario in Rules only; a real case gets the whole gate.
• How a case is released, in order: the receiver's dry run comes before the approval, which binds that dry run, the plan, the evidence, the policy and site profile versions and the receiver's version and epoch, and expires after an hour.
• A hospital's install commands switch the demo off (-Ddemo=0), and a new site install starts in shadow mode, which sends no recovery write and no escalation email.
• Turning off a receiver's answer checks (strict_answers: false) is described as a weaker contract, not a fix.
• Documents, outages and receivers: the switches a document exception needs, Outage Mailer and Read again, and one mapped operation through the receiver's API.
• The results state what each figure measures, release by release.

Tested: the full CI on GitHub against IRIS, plus the web and browser suites.

Full change log: https://github.com/MxSalata/shutter/blob/main/CHANGELOG.md

Documentation, recorded evidence and judge-tooling update. No native code changes. The keyless launcher now pins verified native 0.3.2 explicitly, so publishing a newer package cannot move its install target. The local candidate verifier supports an offline literal install and checks installed identity. The recorded held-out wrong-delivery/review trade-off and three source-linked prose examples are easier to inspect. Includes the recorded evidence tour and receipt inspector. Native package 0.3.3; separate React workbench 0.2.1. Agent, deterministic policy, runtime sources and frozen evaluation records are unchanged; no new evaluation was run.

ISAIAH 0.2.0 — Developer Tools and FHIR Interoperability

ISAIAH began with a principle: an agent's answer isn't enough. We need to understand what it observed, verify its conclusions, and retain evidence of what actually happened.

Version 0.2.0 extends that approach beyond the original R17/R29 interoperability investigations into developer tools, interface inspection, and a controlled HL7-to-FHIR workflow.

What's New

• FHIR R4, R4B, and R5 OpenAPI export. Generate standalone OpenAPI 3.1 documents from approved local FHIR CapabilityStatements. The exporter includes advertised resource read/search operations, identifies omitted capabilities, and keeps advertised behavior separate from verified endpoint behavior. This implements the read/search portion of Community Idea DPI-I-804.
• Version-aware HL7-to-FHIR delivery. The generated synthetic Organization application was qualified against isolated local HAPI endpoints for R4, R4B, and R5. It binds delivery evidence to the destination, rejects version mismatches and conflicting resources, and handles duplicate requests and uncertain responses without blindly repeating writes.
• AI-assisted test proposals. Native AI Hub can propose bounded synthetic test inputs. ISAIAH derives expected results from a reviewed contract; model output does not directly become executable code or deployment authority.
• Interface and message-type inspection. Compare declared ObjectScript message types with independently observed trace information and generate reviewable, versioned synthetic interface artifacts.
• Evidence-linked developer guidance. Coach, Focus, and Companion present the same underlying facts while adapting the level of explanation.

Installation and Qualification

The 0.2.0 native IPM package passed clean installation on IRIS for Health Community AI Hub 2026.3.0AI Build 154U. A targeted upgrade from public IPM 0.1.0 to the qualified 0.2.0 archive also preserved existing synthetic receipts and message history.

The separate Node workflow passed clean-install testing and local R4/R4B/R5 delivery checks. The retained release review reports 44 passing offline tests, with two optional Hermes checks skipped.

Current Boundaries

ISAIAH remains an open-source local developer preview using synthetic data, not a production or clinical integration system.

The generated Organization workflow is intentionally narrow. OpenAPI export describes advertised capabilities; it does not establish access permissions or prove live endpoint behavior. Shared or untrusted writable project directories, general Node/Compose migrations, and unrestricted application generation are not qualified.

The public interactive demonstration is a simulation. The downloadable R17/R29 recording shows genuine earlier native execution, with its recording limitations disclosed.

Explore ISAIAH

• GitHub repository and installation instructions
• FHIR OpenAPI walkthrough
• Developer workflow documentation
• Interactive simulation
• Media gallery

Developed under the direction of Kenneth J. Smith with AI-assisted development and evidence-based verification.

SynapseHealer v1.0.1

🚀 Highlights

1. Native InterSystems Workflow Engine Routing

• Role Delivery: Created and verified the SynapseReviewers workflow role via Synapse.Config.WorkflowSetup, populated with authorized clinician/operator users.
• Two-Way Action Handling: Native Approve and Reject actions executed in the IRIS Workflow Inbox now invoke Synapse.Workflow.ReviewTaskResponse to transition local queue states and dispatch payloads to ResubmitDeliveryOp or QuarantineVaultOp.
• Portal Integration: Added deep-link navigation directly from the dashboard into the native InterSystems Zen Workflow Worklist (/csp/sys/%25CSP.UI.Portal.WorkflowWorklist.zen).

2. IPM (InterSystems Package Manager) Certification

• Verified module.xml specification for automated registration on the IPM Community Registry.
• Removed packaging artifacts that caused zpm load failures, enabling standalone installation via:

  zpm "install synapse-healer"
  

3. 24-Point Automated Verification Suite

• Added scripts/smoke_test.sh providing 24 automated checks across:
  • Idempotent workflow setup.
  • Role existence and active reviewer memberships.
  • Interoperability production runtime checks (Synapse.Production).
  • Task creation, task claim, approval, and rejection.
  • End-to-end execution of all 7 canonical HL7 and JSON replay scenarios.

4. Observability Dashboard Polish (ui/)

• Pipeline Stepper Animation: Visual step-by-step illumination across the 4 stages ($1 \rightarrow 2 \rightarrow 3 \rightarrow 4$) with smooth auto-scroll to the Diff Studio.
• Diff Token Badging: Exact mutated tokens glow in rose (1985-02-31, unescaped |, quoted strings) vs emerald (19850228, \F\, native types).
• HL7 Segments: Segments (MSH, EVN, PID, PV1, OBX) are split onto individual numbered lines.
• Presenter Reset: Added a one-click Reset control in the top bar to zero out counters on camera for video demos.
• Realistic Telemetry: Realistic latency variance derived from individual tool runtimes replacing flat static metrics.

---

Full Commit Diff: v1.0.0...v1.0.1
License: MIT
Author: Joseph Bassey John [email protected]

Suspend, resume and reroute, with a dry run

• Ask OcuTalon in the chat to suspend or resume an item of a watched production, or to reroute an incident's failed messages to another item. Each comes as an approval request with its own dry run: the item's state before and after, or the count, the current and new target and one example.
• Nothing changes until you approve, and after you approve the request's card shows what happened.
• While the incident is open, a suspend is undone the same way, by asking OcuTalon to resume the item. After it closes, enable the item again on the production's configuration page in the Management Portal.
• On the online demo every visitor shares the Orders production, so there OcuTalon offers the reroute only. Try it: after the guide's incident, More to try, Reject a fix, then Reroute the failed orders.

Partner delay notices, sent only after approval

• Ask OcuTalon in the chat to warn the partner about an incident's delay. It drafts a short notice from the incident's count, times, affected flow and cause, never from a message's contents, and raises it as an approval request that shows the exact text and every recipient.
• Nothing is sent until you approve. In demo mode the partner contacts are simulated and the approved notice goes to the Simulated mailbox, not to a real inbox.
• Try it: after the guide's incident, More to try, Warn the partner.

The Memory card: pinned and learned memories

• All memories lists what OcuTalon remembers, each marked Told or Learned, with Pin, Unpin and Forget on each and a search box.
• Pinned shows the facts read at the start of each conversation and how much of their 1,000-token limit (an estimate) they use.
• When OcuTalon keeps a fact you didn't ask it to remember, OcuTalon's code adds a line after the reply in the web chat and in Telegram: I'll remember this: "…". You can tell me to forget it. The line doesn't depend on the model.
• Try it: More to try, Pin a memory.

A Usage page

• Open Usage in the header to see your tokens and cost by day, agent, channel or model, counted per turn and per decision, with each day's largest model request (an estimate) against the 100,000-token limit.
• On the online demo you see only your own session's use. Try it: More to try, See tokens and cost.

A History page

• Open History in the header to look back at the decisions OcuTalon made on your messages, filtered by outcome, channel, date and fallback, each with its reasons and a link to its trace, and at your incidents with their state and, once closed, their summary.
• On the online demo you see only your own session's decisions and incidents. Try it: More to try, Look back at past decisions.

More to try, in four groups

• The guide's More to try panel now has 14 items under four headings: Incidents and fixes, Memory and documents, Safety and settings, and Usage and history.

Docs and CI

• The README's logo now uses a full web address, so it shows wherever the README is read.
• CI's browser and install tests now wait for a busy test port and retry once it is free, instead of failing.

Requires the InterSystems IRIS for Health AI Hub Early Access image, build 154 or build 109. Upgrading from 1.0.6 keeps your conversations, reminders, watches, approval requests, settings, memories, documents and Telegram pairing. The online demo runs 1.0.7.

---

Online demo: https://demo.ocutalon.com · Open Exchange: https://openexchange.intersystems.com/package/OcuTalon

Java PEX receipt exporter added to the native production. It exports signed, immutable JSON receipts after routing commits; retries reuse the original receipt, and export failures preserve the route. Receipt provenance follows the saved investigation mode. Includes the citation-completeness fix without changing deterministic policy. Verified on IRIS AI Hub 2026.3.0AI.154.0 / 154U ARM64, including a fresh offline 0.3.2 archive install. React workbench remains 0.2.1. Code, verification and limits: SilentShift 0.3.2.

Update deployment code and run code
Add picture

Address the issues raised by the experts

Updated walkthrough and documentation

• Added an inline video walkthrough to the application description.
• Demonstrates the current case interface, evidence review, and human decision process.
• Explains the reviewer and investigator agent roles.
• Improved narration timing and transitions, with English captions.
• Added a public watch page and downloadable MP4 requiring no sign-in.

The walkthrough includes synthetic practice scenes and a replay of retained evidence from the November 5 IRIS investigation.

Watch the walkthrough (3:55)

Download the MP4

Shutter 1.4.3 opens the online demo up for judges, with clearer words throughout. No new recovery features.

• The judges' account can play the scenarios on the online demo, S8 with the real agents included, within its own model budget share; only an operator or approver can reset the shared demo.
• On the demo, the site profile, agents' library and review annotation editors work as an approver's do, and their Save is locked: the demo's settings are never changed.
• Orders and results are described as they work since 1.3.0 and 1.4.0: findings for a person, and the approved outage resend.
• The Scenarios page: what each run mode does, and clearer scenario titles and summaries that put the decision first.
• Fixes: the tour's arrow no longer touches its section, and the scenario diagrams hold still when switching modes.
• Tested: the unit suites on AI Hub build 154 and IRIS 2026.2, the role checks for the judges' and demo accounts, and the browser suite.

Full change log: https://github.com/MxSalata/shutter/blob/main/CHANGELOG.md

Adds an IPM module for the Chronos ObjectScript production. The package requires IRIS 2026.3 or later with Interoperability enabled. A clean IRIS AI Hub 154U instance loaded the 1.0.2 archive with IPM 0.10.10 and compiled all 39 source classes. The full application runs through the existing Docker Compose setup. Installation instructions.

Native IRIS Workflow review task when the gate rejects an AI proposal (the reviewer's action does not change the stored result). IPM package now includes the worker's benchmark and replay recordings; one admin step, Storm.Review.Setup(reviewer), sets up the review role. demo.sh prints the Visual Trace session of storm A1.

Where an answer came from

• An answer from your documents now ends with a chip for each source, naming the document and its section. Press a chip to read the passage, or open the whole document on the Documents page.
• An answer that recalls a memory carries a From memory chip that shows what was remembered and when.
• Try it on the online demo: More to try, See where an answer came from.

A sample runbook in one press

• No file to hand? On the Documents page, press Add the sample runbook. A short runbook about the demo's Orders feed is added through the same upload as any file, and the button hides once it is in your list.
• When it reads Ready, ask "According to the runbook, what should I do when partner orders fail with a date error?" and look for the chip under the answer that names the runbook and its section.
• Try it: More to try, Ask about a document.

Incident summaries

• When an incident closes, OcuTalon writes a summary from its own records, with no extra model request: the timeline, the cause and evidence, each approval with its channel and time, the messages affected and the incident's model cost.
• It arrives in the chat and on the Simulated phone (and in Telegram when it is paired on your own install), and you can ask for it again in the chat.
• Try it on the online demo: after the guide's incident, More to try, Read the incident summary.

Memory: told or learned, and core memory

• Each memory now records whether you asked OcuTalon to remember it (told) or OcuTalon kept it from something you mentioned (learned). OcuTalon's code decides this from your own words, not the model. When the chat names a memory, it says "(told)" or "(learned)".
• Core memory: a pinned memory is given to the model at the start of every conversation, under a hard cap of 4,000 characters. A pin that would go over the cap is refused, and nothing changes. The web routes to list, pin and forget memories are in this release; the Memory card's pin button comes in the next one.
• Fixes: a first message of the day that fails before it reaches a model no longer uses up the day's session start, and today's notes no longer repeat your current message back to the model.

The heartbeat resumes itself

• If IRIS's Task Manager leaves the OcuTalon heartbeat task Suspended, for example after an update, every start now resumes it and writes one warning line to the start log. Before, background checks, watches and the digest's checks could stay paused until someone resumed the task by hand.

Groundwork for MCP servers and email

• The names and contracts for the next step are in place: a table of registered MCP servers that records each attach, the commands to manage them (admins only), a send-email command that from the chat can only send to your own mailbox address, and a record of which sessions belong to admins. Nothing here changes what you see yet.

Docs, install and CI

• The README opens with a header: the logo, a one-line description, and badges for CI on main, the latest release, the online demo's live status, Docker, IPM, AI Hub and the licence. It also names the contest the entry is for.
• The Dockerfile now sits at the repository root. Its content is unchanged, and ./install.sh works as before.
• CI's IRIS tests now run in 16 groups, so every group finishes well inside its time limit.

Requires the InterSystems IRIS for Health AI Hub Early Access image, build 154 or build 109. Upgrading from 1.0.5 keeps your conversations, reminders, watches, approval requests, settings, memories, documents and Telegram pairing. The online demo runs 1.0.6.

---

Online demo: https://demo.ocutalon.com · Open Exchange: https://openexchange.intersystems.com/package/OcuTalon

This release comes from a full end-to-end smoke test of the portal. Every feature was exercised in the browser, and the issues found were fixed and re-tested.

Bug fixes
Dialogs work again. “Add to dashboard”, “Create view” and “Schedule report” closed their dialog without doing anything. The cause was that the dialog’s close event doesn’t fire in some embedded browsers. Dialogs now read their result directly from the OK button, the Cancel button and the Esc key.
Views with ORDER BY. IRIS rejects ORDER BY in a view unless the query also has TOP (SQLCODE -143). The portal now adds TOP ALL automatically, so any result can be saved as a view.
Management Portal links. The README now uses the correct IRIS for Health paths (/csp/healthshare/copilot/...) for the Production Configuration and Message Viewer pages.
More accurate AI answers
Insights use totals computed by IRIS. When the AI summarizes a result, IRIS now calculates the sum, average, minimum and maximum of every numeric column across all rows. The model is told to quote those figures and never to add up or average rows itself. It may only compute a percentage for a single row. Before this fix, generated totals could be off.
Explain stays factual. Query explanations describe only what the SQL actually does. If the business glossary defines a rule that the query doesn’t apply (for example, excluding cancelled orders), the explanation says so instead of assuming it.
AI Analyst answers from the current turn. The agent uses only data returned by its tools in the current turn, never numbers or SQL from earlier answers.
Better handling of large catalogs
Question-aware catalog ranking. When more than 20 tables are visible, the copilot ranks them by relevance to the question before building the prompt, so the right tables are always included. A table scores higher when the question mentions its name, its columns or a glossary term, and related tables get a small bonus.
Source-scoped glossary. Only the business terms that apply to the selected sources are sent to the AI.
Verified in this release
Login and languages: login works, and the EN/PT-BR switch works.
Ask: charts, tables, insights, Refine and follow-up suggestions.
AI Analyst and source guard: the agent answers correctly. The source guard blocks questions about data outside the selected sources.
Dashboards: real-time refresh with simulated live orders, “Generate with AI”, and editing or removing widgets.
SQL editor: Run, Explain and Refine, plus the read-only SQL guard.
Views: create, query and delete.
Catalog and glossary: catalog filter and refresh, and adding, editing and deleting glossary terms.
History: reopening past queries.
Interoperability: the production is running, “Run now” on a scheduled report produces the AI report, and the full message trace is shown.
IRIS Management Portal: reachable through the Web Gateway.

Shutter 1.4.2 is a fix for the public demo's sign-in page. No new features.

• The sign-in page says the live hospital is on when it is: a visitor who isn't signed in now sees the full line (a real IRIS for Health instance with AI Hub, its build, made-up patients, a new failure every 7 minutes, reset on the hour). The signed-out health answer gives only whether the live hospital is on and how often it fails, and nothing once the hospital's player stops.
• Tested: the unit suites on AI Hub build 154 and IRIS 2026.2, a new end-to-end check on an install hardened like the demo, and the browser suite.

Full change log: https://github.com/MxSalata/shutter/blob/main/CHANGELOG.md

Compose one-command launcher, verified judge path, docs refresh.

Shutter 1.4.1 fixes what the hands-on recheck of 1.4.0 found. No new features.

• A resend whose result was unknown now settles by itself once the engine shows how it ended, and its case follows.
• The outage card shows each message once at its latest state, with counts that match what happened.
• No approval button appears before the recovery control has been read.
• A shadow-mode escalation reads Not sent.
• Orders, results and documents get words that are true in 1.4.0, and their findings one line each.
• The outage pause field's example date is in the future.
• Tested: all 56 rows of the pathology rig on AI Hub build 154, the unit suites on 154 and IRIS 2026.2, the browser suite, and each fix checked by hand.

Full change log: https://github.com/MxSalata/shutter/blob/main/CHANGELOG.md

README: live read-only online demo for judges

README: contest bonuses section and downloadable demo video

Shutter 1.4.0 completes pathology: after one approval, Shutter resends an outage's messages that never reached the receiver, one at a time, in order, through the engine itself.

• One approval of an outage's offered messages, then Engine Resend sends them in order, reading every rule again before each one and stopping at the first that doesn't complete. Stop Shutter recovery and shadow mode hold it too.
• Messages the receiver already holds close as already delivered; at a receiver of unknown duplicate handling, an approver can close a message as handled by hand. Nothing is sent for either.
• The patient check, narrowed for orders and results: results on other orders still go, while anything on the same order, a merge of the patient, or anything unread still holds.
• Fixed: the findings on an order or result case now reach the case (1.3.0's known issue).
• An email written with no mail server reads "Saved, not delivered", never Sent.
• The Evaluation page's approval safeguards as a compact list, and the outage card and case page saying what happened.
• F03 and F07 played live on 1.3.2: right in all 12 agent runs on the board and the single investigator.
• Tested: all 56 rows of the pathology rig on AI Hub build 154, the unit suites on 154 and IRIS 2026.2, the browser suite, and a hands-on test before release.

Full change log: https://github.com/MxSalata/shutter/blob/main/CHANGELOG.md

update readme

Demo link updated: https://8b79-2804-1928-216d-4301-ed37-88a5-1969-d364.ngrok-free.app/

Included a pre-built Tester Agent that can be used in the public demo. This implements idea: DPI-I-439

Demo updated