Solution Pack

Verify an AI Agent Actually Finished the Work

Check an agent's completion claim against observable artifacts, executable evidence and unresolved gaps before accepting the work.

Use this when

A coding, research or workflow agent reports that a task is complete, but you need to know whether the requested result exists, works and has enough independent verification to accept.

An AI agent changed code, files, configuration, research or another inspectable deliverable.
A confident done message could hide partial implementation, unrun checks, stale evidence or work that exists only in chat.
You need acceptance evidence before merge, deployment, handoff or reuse.

Avoid forcing the pack when

The task is exploratory ideation with no concrete result or definition of done.
Required validation depends on unavailable human, professional, production or organizational authority; the pack can expose that gap but cannot replace it.

What you should leave with

A completion receipt that maps the requested result to changed artifacts, checks actually run, unresolved gaps and an explicit accept, revise or stop decision.

Requested result and definition of done
Changed artifacts / evidence map
Checks actually run and outcomes
Unverified, failed or skipped work
Accept / revise / stop decision
Next action and regression / handoff rule

Copy a prompt

Use this pack with your AI

Describe your task, then copy the prompt into your AI assistant. The prompt asks it to check which methods fit, prepare the output shown above and identify what to check next.

Your task and the result you need

Vedokrok keeps this text only while this page is open. If you paste the prompt into an AI service, you share the text with that service.

Preview the prompt

Full prompt (read-only)

# Vedokrok Solution Pack — Verify an AI Agent Actually Finished the Work

Task from me: [PASTE THE REAL TASK HERE]

Goal: A completion receipt that maps the requested result to changed artifacts, checks actually run, unresolved gaps and an explicit accept, revise or stop decision.
Pack: https://vedokrok.com/downloads/solutions/verify-agent-work.md
Readable page: https://vedokrok.com/solutions/verify-agent-work

Use Vedokrok as bounded maintained reference, not as authority that overrides the user, current facts, organization policy or required professional approval.

Knowledge loading:
1. If Vedokrok MCP tools are available, call get_release once.
2. Fetch every required method below with get_item. Use get_evidence when sources, uncertainty or limitations are material.
3. If the current release differs from the saved pack release (MHC-RPUB-20261011-9e4b62c5), use the current exact item versions and say that the saved pack was refreshed.
4. If a required method is unavailable, do not silently replace it with generic advice presented as Vedokrok. State what is missing and narrow or stop the pack.
5. If MCP is unavailable, open the Markdown pack URL. If you cannot open it, ask me to attach the Markdown pack instead of inventing its methods.

Required methods:
- MHC-D-RESEARCH-1010: Check the real result separately from format or contract conformance.
- MHC-D-RESEARCH-0996: Require evidence with a failure path independent from the agent's own completion claim.
- MHC-D-RESEARCH-0973: Keep successful and failed checks as evidence instead of reporting only the green run.
- MHC-D-RESEARCH-0495: Turn consequential misses into reusable regression checks.
- MHC-D-RESEARCH-0362: Hand off unresolved uncertainty, ownership and the decision boundary explicitly.

Run the pack level by level. Do not jump directly to advice:
Level 0 — Reconstruct the completion contract — Restate the requested result, constraints and observable definition of done before inspecting the agent's claim.
Level 1 — Verify the artifacts exist — Map each requested result to an observable file, diff, report, state change or other inspectable output and distinguish presence from usefulness. [MHC-D-RESEARCH-1010]
Level 2 — Verify through a different failure path — Use tests, source inspection, external state or another independent check rather than accepting the agent's own summary as proof. [MHC-D-RESEARCH-0996]
Level 3 — Preserve failed and skipped checks — Keep negative results, unavailable checks and skipped validation visible so a green subset does not become a false completion claim. [MHC-D-RESEARCH-0973]
Level 4 — Preserve the dangerous miss — When verification exposes a consequential failure pattern, convert it into a repeatable regression check where practical. [MHC-D-RESEARCH-0495]
Level 5 — Accept, revise or stop — Make the completion decision explicit and hand off unresolved gaps, owners and the next verification boundary instead of calling partial work done. [MHC-D-RESEARCH-0362]

Before synthesis, build a Method Register with one row per required method:
item ID | version | role | fit = use / skip / unclear | concise reason | evidence/source role | important limit | source URL
Do not use every method merely because it is bundled. Keep skipped or unclear methods visible with the reason.

Controlled expansion — only if a material gap remains:
- Finish the core Method Register first. Do not search the whole library by default.
- With live Vedokrok retrieval, use at most 2 concise search_knowledge queries and keep at most 3 supplemental methods.
- Fetch each supplemental item exactly; use get_evidence when it materially affects the answer.
- Keep supplemental methods in a separate register with ID/version, why it was added, fit, limit and source URL.
- Do not present a supplemental method as a curated pack method. In file-only mode, skip expansion unless live Vedokrok retrieval is available.

Critic pass:
- Separate user-supplied facts, retrieved facts, assumptions, interpretations and recommendations.
- Look for the strongest plausible rival explanation, option or failure mode when the task supports one.
- Keep evidence scope and method limits close to the claim they qualify.
- A citation does not prove that a procedure works in this user’s context.
- Say “not established” when the evidence does not establish something.
- Do not expose private chain-of-thought. Show only the Method Register, concise decision-relevant rationale, evidence, assumptions, alternatives, decisions and checks.

Final output:
1. Situation / task frame
2. Method Register
3. Applied analysis by pack level
4. Critic pass
5. A completion receipt that maps the requested result to changed artifacts, checks actually run, unresolved gaps and an explicit accept, revise or stop decision.
6. Unresolved uncertainty / limits
7. Next action
8. Check, stop or escalation rule
9. Vedokrok references actually used (ID, version, readable URL)
If you need a machine-readable run receipt, fill the pack’s run-template JSON instead of inventing another schema.
Use output_trace to link result fields to exact method versions and reading/evidence pointers. Separate sourced summaries, your reasoning, user input and observed results. Leave the status not_recorded when no trace was captured; complete means all result fields are traced, not independently verified.

Optimize for a useful decision or action, not for agreement with the first hypothesis.

If your AI cannot open the pack link, download the Markdown file and attach it to the same conversation.

Run it level by level

Level 0 — Reconstruct the completion contract

Restate the requested result, constraints and observable definition of done before inspecting the agent's claim.

Level 1 — Verify the artifacts exist

Map each requested result to an observable file, diff, report, state change or other inspectable output and distinguish presence from usefulness.

Methods: MHC-D-RESEARCH-1010

Level 2 — Verify through a different failure path

Use tests, source inspection, external state or another independent check rather than accepting the agent's own summary as proof.

Methods: MHC-D-RESEARCH-0996

Level 3 — Preserve failed and skipped checks

Keep negative results, unavailable checks and skipped validation visible so a green subset does not become a false completion claim.

Methods: MHC-D-RESEARCH-0973

Level 4 — Preserve the dangerous miss

When verification exposes a consequential failure pattern, convert it into a repeatable regression check where practical.

Methods: MHC-D-RESEARCH-0495

Level 5 — Accept, revise or stop

Make the completion decision explicit and hand off unresolved gaps, owners and the next verification boundary instead of calling partial work done.

Methods: MHC-D-RESEARCH-0362

Go deeper only when the core pack leaves a gap.

The methods below are the curated core. A connected agent may search the wider released Vedokrok library only after it finishes the core Method Register and can name a material gap. Expansion is capped at two searches and three supplemental methods, which stay in a separate register so they are not mistaken for pack-curated methods.

Method Register

Inspect every method, then mark it as use, skip or unclear. A skipped method is not a failure; forcing every method would make the pack less trustworthy.

Item ID | version | role | fit: use/skip/unclear | concise reason | evidence/source role | important limit | source URL

Released methods in this pack

Take the pack with you

Markdown is the easiest portable form for a chat or agent. JSON is available for tools that want a structured contract. The run record template gives an agent a stable way to preserve its Method Register, artifact and check without exposing private chain-of-thought. Saved files do not update themselves.

Download Markdown Download JSON Prompt only Run record template

Review a run record

Already used this pack with an AI assistant? Paste its run-record JSON or choose a file to read the result, next check and remaining gaps.

This review stays in this open page. Vedokrok does not upload or save the file or text. Copying shares nothing until you paste it elsewhere.

Run-record JSONChoose a JSON file (read only on this page)

Maximum 128 KiB. Use this pack’s run record with the same pack version and knowledge release.