Agenda Intelligence MD

Agenda Intelligence MD is a deterministic evidence-packet linter for claim-backed AI output.

Give it claims, the source IDs each claim relies on, optional quotations, and the supplied source text. It returns broken references, quote mismatches, lexical-support gaps, unmatched numbers, and the next reviewer actions.

It reports packet completeness, not whether a claim is true:

• not a factuality verifier;
• no autonomous live source retrieval;
• no authorization, approval, or compliance decision;
• human review is required for every result.

PyPI version CI License: MIT

First run

Run the canonical synthetic packet from a source checkout:

git clone https://github.com/vassiliylakhonin/agenda-intelligence-md
cd agenda-intelligence-md
python -m venv .venv
.venv/bin/python -m pip install -e .
.venv/bin/agenda-intelligence check examples/evidence-packet/request.json

Expected shape:

packet_status=packet_complete claims=2 sources=1 factuality=not_assessed
  c1: packet_complete (lexical_support=supported, coverage=1.0)
  c2: packet_complete (lexical_support=supported, coverage=1.0)

Use JSON for an agent loop or CI pipeline:

.venv/bin/agenda-intelligence check examples/evidence-packet/request.json --format json
.venv/bin/agenda-intelligence check examples/evidence-packet/request.json --strict

--strict exits non-zero unless every claim is packet_complete.

Install the pinned release without cloning the source and check your own packet:

pip install "agenda-intelligence-md==1.3.0"
agenda-intelligence check /path/to/evidence-packet.json --strict

The evidence-packet contract

The request has two required collections:

• claims: a claim ID, claim text, declared source_ids, and optional verbatim quotes;
• sources: a source ID and the text supplied by the caller.

Request schema: schemas/v1/evidence-packet-request.schema.json

Response schema: schemas/v1/evidence-packet-response.schema.json

Runnable example: examples/evidence-packet/request.json

The response has three packet statuses:

Status	Meaning
packet_complete	References resolve and the named source text has strong lexical overlap with the claim.
source_review_required	References resolve, but lexical support is weak or a numeric value is not present.
packet_incomplete	A source is missing, a quote is absent, or the claim has no source reference.

factuality_status is always not_assessed. A complete packet can still rely on a wrong, stale, biased, or irrelevant source.

Python API

import json
from pathlib import Path

from agenda_intelligence.services import check_evidence_packet

packet = json.loads(Path("examples/evidence-packet/request.json").read_text())
result = check_evidence_packet(packet)
print(result["response"]["packet_status"])

The service layer is stateless. It does not persist packet contents or fetch missing sources.

What this is

• A small JSON contract for claim-backed AI output.
• A deterministic preflight before human review.
• A CLI and Python service suitable for local and CI use.
• An inspectable base for domain-specific compatibility profiles.

What this is not

• A general LLM evaluation platform.
• A GRC, vendor-management, or document-storage system.
• An agent authorization or policy-enforcement layer.
• Legal, compliance, sanctions, financial, investment, insurance, or trading advice.
• Proof that a source or claim is factually correct.

Why a repo full of markdown?

The repository predates the evidence-packet focus and also packages agent reasoning instructions. Files under skills/ are executable instructions for compatible agent runtimes, not ordinary prose documentation. They remain available for compatibility, but they are not the primary product interface.

MCP

The packaged MCP server remains available for existing clients:

{
  "mcpServers": {
    "agenda-intelligence": {
      "command": "uvx",
      "args": ["--from", "agenda-intelligence-md", "agenda-intelligence-mcp"]
    }
  }
}

The canonical evidence-packet preflight is currently exposed through the CLI and Python service. Existing MCP tools such as audit_claims, verify_quotes, grounded_check, and verify_claims remain compatible; no tool was removed or renamed. See MCP.md.

Claude Code plugin installation also remains available:

/plugin marketplace add vassiliylakhonin/agenda-intelligence-md
/plugin install agenda-intelligence@agenda-intelligence

Compatibility profiles and adapters

The strategic-intelligence shell, HTTP API, A2A adapter, Cloudflare Workers, and five domain profiles remain in the repository. They demonstrate how the same service layer can be wrapped for different transports and domains. They are not the default commercial wedge and do not establish product-market fit.

Compatibility surface	Reference
Strategic agenda analysis	Agenda-Intelligence.md
HTTP API	docs/deployment/http-api.md
A2A adapter	docs/deployment/a2a-adapter.md
Middle Corridor example	docs/use-cases/kazakhstan-middle-corridor.md
CIS secondary-sanctions example	docs/use-cases/cis-secondary-sanctions.md
Agentic interaction example	docs/use-cases/agentic-interaction-trust.md
Gulf maritime example	docs/use-cases/gulf-maritime-exposure.md
Kazakhstan market-entry example	docs/use-cases/kazakhstan-market-entry-readiness.md
Live A2A demo pack	docs/agenstry/demo-pack.md

The compatibility profiles are evidence-routing examples only. They do not provide legal, compliance, sanctions, financial, investment, insurance, or trading advice. Human review is required before any commercial action.

Verification Contract

The repository keeps three checks separate:

1. check reports packet completeness and lexical-support diagnostics.
2. grounded-check performs the older claim-to-corpus lexical diagnostic.
3. verify-claims applies declared freshness, authority, independence, jurisdiction, and identifier rules to caller-supplied evidence.

None discovers the right sources for the caller. verified in the bounded Claim Verdict contract means the supplied evidence meets that declared contract; it is not absolute truth.

Schemas

Canonical schemas live under schemas/v1/. Packaged copies under src/agenda_intelligence/data/schemas/v1/ must remain byte-equivalent; CI checks this invariant.

Start with:

• evidence-packet-request.schema.json
• evidence-packet-response.schema.json
• evidence-audit.schema.json
• claim-verification-request.schema.json

The full registry is in agent-manifest.json.

Before / after and benchmarks

The older agenda-analysis evaluation surface remains available for regression and compatibility work:

• examples/before-after/eu-ai-act.md
• examples/before-after/red-sea-shipping.md
• examples/before-after/sanctions-routing.md
• examples/source-backed/eu-ai-act.md

These are evaluation fixtures, not customer evidence or production benchmarks.

AnalysisBank

analysis-bank/ contains compatibility fixtures for reasoning-memory retrieval and failure-pattern regression. It is not part of the primary evidence-packet workflow.

Status

Surface	Status
Evidence-packet request/response schemas	Implemented
check_evidence_packet Python service	Implemented
agenda-intelligence check packet auto-detection	Implemented
Legacy agenda-brief behavior for check	Preserved
Evidence-packet MCP tool	Not implemented; use CLI or Python
Live source discovery	Not implemented
Factuality determination	Not implemented by evidence-packet preflight
Paying customers or named pilots	None claimed

Current classification: portfolio-proof / build-to-learn.

Documentation

Topic	File
Adoption	ADOPTION.md
Quickstart	docs/quickstart.md
Evidence audit	docs/evidence-audit.md
Factuality boundary	docs/factual-verification.md
Evaluation	docs/evaluation.md
Source policy	SOURCE_POLICY.md
Security	SECURITY.md
Threat model	docs/threat-model.md
Roadmap	ROADMAP.md

Repository layout

schemas/v1/                    public JSON contracts
src/agenda_intelligence/       Python service and transport adapters
examples/evidence-packet/      canonical packet example
tests/                         contract and regression tests
skills/                        compatibility agent instructions
deploy/cloudflare-worker/      compatibility Worker implementation
docs/                          reference and compatibility documentation

Development

pip install -e ".[dev]"
make ci

make verify-local also runs the compatibility Cloudflare Worker tests.

Roadmap

The next decision is adoption, not another vertical worker: test the evidence-packet contract on redacted practitioner artifacts, measure repeat use, and keep it portfolio-only if no repeated workflow appears. See ROADMAP.md.

License

MIT