AI can do the work. Foundry makes the work dependable.
Foundry is a provider-neutral operating layer for repeatable AI work: explicit authority, durable workflows, traceable context, human approval, and evidence that survives the chat window.
The concept in one line
Deterministic software keeps the books. AI handles judgment. Humans retain consequential authority.
Why it exists
A capable agent is not yet a reliable way of working.
General agents are excellent at adaptable judgment. Repeated workplace tasks need something else around them: a defined job, approved knowledge, bounded tools, recoverable state, measurable quality, and a person who still owns the decision.
The governed work loop
Judgment moves. Authority does not.
Define the job
Mission, scope, evidence, tools, budgets, and success are versioned before the run.
Assemble context
Only approved, bounded, source-traceable material crosses into model judgment.
Run and checkpoint
Deterministic steps and AI decisions are recorded. Interrupted work resumes safely.
Human gate
Consequential effects stay blocked until an authorized person approves the exact outcome.
The architecture
Reuse the procedure. Keep trust local.
Foundry separates portable machinery from private context and from the model providing judgment. A reusable Skill carries instructions—not repository access, credentials, approval power, or a hidden data destination.
Portable core
The operating machinery
Contracts, workflow execution, checkpoints, adapters, evaluations, budgets, and event history.
Isolated workspace
The trust boundary
Agents, approved knowledge, installed Skills, resource grants, private state, and local runtime policy.
Replaceable runtime
The judgment engine
Hosted or local models sit behind one validated boundary. The provider does not own the workflow.
Where it stands
Five chapters built. The sixth is being proven.
Foundry is not a finished platform. It is an executable research-and-build program with complete foundations through durable workflows, and active work turning one proven procedure into a capability that transfers cleanly.
- 00Complete
Foundation
Validated state, append-only events, contracts, and a tested command surface.
- 01Complete
One real cycle
A bounded, human-approved build cycle with decisions, artifacts, and a recorded outcome.
- 02Complete
Hardened harness
Provider-neutral model calls, tool authorization, recoverable transitions, and exact provenance.
- 03Complete
Context that earns trust
Source-hashed retrieval, bounded cited context, and measured grounding instead of prompt stuffing.
- 04Complete
Durable work
Checkpointed workflows, retries, budgets, parallel joins, authorized effects, and human gates.
- 05Active
Reusable capabilities
Promoting proven procedures into portable Skills without smuggling data or authority with them.
- 06Next
Generalization
Prove the system transfers to a second, unlike product and remove assumptions that do not travel.
Evidence, not theater
The system is allowed to find itself wrong.
Tests and subtests passing
Verified against the current working tree on August 31, 2026.
Frozen Skill-routing cases
The first run scored 7/8. The false positive became a tighter boundary; the identical rerun passed all eight.
Model-owned human approvals
A model result cannot approve itself, even when its structure is valid.
A recent correction
Safe execution was not the same as a good answer.
A read-only Steward run passed structural checks but produced an answer that was not grounded or coherent enough to trust. Human approval exposed that the evaluation had measured execution safety without adequately measuring answer quality.
Foundry now separates those scores, blocks approval unless both pass, rejects several deterministic failure patterns before the human gate, and accounts for failed or rejected model calls instead of making their cost disappear.
The new gate is implemented and tested. A fresh end-to-end model result that earns the stricter quality proof is still outstanding.
What remains
Prove transfer, then broaden.
The immediate work is to re-earn the Steward quality proof under the stronger gate, generalize output evaluation beyond one repository, and run the complete capability against an unlike codebase. After that, a second private product will test whether Foundry's procedures travel beyond software-project stewardship.
The assessment
Foundry is already more than a concept: its core boundaries, retrieval, workflow durability, workspace isolation, evaluation machinery, and first reusable Skill are executable and tested. It is not yet a generally proven platform. Its strongest quality is that the remaining distance is visible in contracts, tests, recorded decisions, and gates that are allowed to stay red.
Back to current projects