BriefLoop.ai / How it works
The chain-of-custody demo on the homepage answers “where did this claim come from?” This page answers the rest: why the duties are separated, what happens after a problem is found, how failures become the next version's tests, and how developers work with agents.
AI drafts and proposes. BriefLoop's deterministic control layer audits and keeps the books. Separation of duties is what makes the output trustworthy.
The chain of custody on the homepage answers “where did this claim come from?” This trace answers “what happens after a problem is found?” Gates block; an agent or human revises; the control plane checks again.
Simulation boundary: the repair example represents a new revision submitted by an agent or human. The gate records, blocks, and re-checks; the old revision and finding remain in the audit trail.
v0.14.0 can export one self-contained three-page read-only HTML from Store/LAJ data: quality status, LAJ advice, and improvement status. It is not runtime authority, a quality score, or a delivery verdict and cannot trigger workflow action. LAJ utility is NOT MEASURED; the improvement page honestly reports Improvement Ledger unavailable.
The homepage has a synthetic preview. All site demos are read-only: no dispositions, writes, automatic learning, or “accept suggestion to improve the next run” capability.
This is a software-engineering responsibility chain, not automatic learning inside a run. A failure may become a code candidate and regression test, but it is not consumed by the current or next brief run. No Store-native Improvement Ledger is available in 0.14.
A missing citation mapping is not hidden in prose. It becomes a finding, blocker, and event with stage, scope, and repair ownership.
No automated AI system should — or can — take over human responsibility for decisions and sign-off. BriefLoop does not approve delivery for you; it gives you an evidence chain that reduces the risk of missing something — traceability, not semantic proof.
"When data conflicts or goes missing, the system exposes the trail and supports fast trace-back."
Preconfigured topologies and audit contracts for research, compliance, and corporate disclosure work.
Monitor industry news, competitor moves, and policy releases. Multi-source collection with entity mapping, producing a weekly brief a human can deliver.
Bring internal financial data and business metrics. Build a frozen, protected Claim Ledger in a strictly isolated offline environment, with traceable attribution for decisions.
Search across prospectuses, audit reports, and regulator letters at scale. Extracted facts anchor to exact pages and highlighted passages, with a complete audit trail for diligence.
BriefLoop separates writing from control. An external agent researches and drafts; the Python CLI creates workspaces, validates artifacts, records transactions, runs gates, and preserves delivery state. The CLI does not generate a brief by itself.
New runs support only the Experimental Codex SQLite path. briefloop status and briefloop runtime next expose Store-derived read-only state and the next action. Finalize, approval, and delivery are typed Store actions through the Codex runtime host. SQLite ControlStore is the sole runtime authority, and the legacy JSON control plane has been deleted. Legacy JSON control files and report, status, Quality Panel, Markdown/JSON/JSONL/HTML exports are non-authoritative projections. Strict action, envelope, and human-request JSON payloads are revalidated against ControlStore and are not authority by themselves.
After installing the Codex runtime kit (briefloop runtime install --workspace <workspace> --runtime codex), open and trust the workspace in Codex. Codex performs only the exact action returned by runtime next and its Receipt-backed role invocation; it never falls back to another runtime.
The current supported bootstrap is this source checkout: it installs the deterministic CLI and keeps source runtime assets together. The Codex path then runs briefloop runtime install --runtime codex inside the workspace — open and trust that directory in Codex afterwards. On Windows, follow the PowerShell installation path; do not translate these Bash commands into Git Bash.