Teammately Docs
Docs menu

concept

Improve

Coordinate durable Improvement Sessions from pinned benchmark evidence through Goal Contracts, candidates, evaluations, trajectories, and frontiers.

Improve

Improve is the benchmark-scoped workspace for coordinating candidate work from benchmark evidence. Each Improvement Session pins the exact starting evidence it uses, including any Benchmark Version, Harness Version, and Run identities. Sessions preserve the goal, authorization, agent and worker activity, candidate Harness Versions, canonical evaluation receipts, and Current frontier.

Definition

A new session begins with Start from evidence. The operator selects the target and relevant benchmark evidence, then prepares a Goal Contract. The contract binds the free-form objective to canonical target identities, measurement bindings, constraints, unresolved items, and intervention boundaries.

The current Improve workspace offers Coevolve, External Agents, and External fine-tuning experiences where enabled. Coevolve supports bounded Work and Evolve behavior; external experiences use explicit handoff or provider boundaries. All retained candidates still rely on observable Harness Versions and canonical Benchmark Evaluations rather than unrecorded claims of progress.

Decision checkpoint

NeedSession choiceRequired evidence
Investigate or implement one bounded directionWorkConfirmed Goal Contract and pinned failures or target evidence
Explore several competing hypothesesEvolveComparable measurement plan and explicit exploration authorization
Delegate implementation externallyWorker packagePinned target, return contract, and observable returned candidate
Decide which candidates remain viableCurrent frontierCanonical evaluation receipts and goal constraints
Stop scheduling new work temporarilyPauseRetained evidence and chronology remain available
Correct missing benchmark meaningContribution or coverage follow-upUpstream policy, rubric, case, or coverage observation is named

Goal Contract and chronology

The Goal Contract is the session's authority boundary. Confirm it only after the target and measurement plan are resolvable. Later revisions should remain explicit rather than silently changing what earlier candidates attempted.

Chronology records durable session transitions, agent activity, proposed approaches, candidates, evaluations, pauses, resumptions, cancellation, and terminal state. Narrated trajectories expose bounded work segments and can identify unannounced durable activity without pretending to know private external-worker behavior.

Candidates and current frontier

A candidate should identify its Harness version, hypothesis, parent or branch context, and evaluation evidence. The current frontier represents retained candidates supported by the latest valid evidence and Goal Contract. It is not synonymous with the most recent candidate or the highest aggregate score.

Evaluation receipts link candidates back to Benchmark Evaluations. If a candidate improves one objective but violates a constraint or regresses a must-level rubric, the frontier should keep that tradeoff visible.

Human and external-worker boundary

Operators can pause, resume, cancel, review, or redirect work through the available session controls. External worker packages can carry the confirmed goal and evidence to Codex, Claude Code, or another worker. Teammately records only returned artifacts and requests that satisfy the return contract; it does not infer private work state.

Worked example

Evolve a grounding harness

The Goal Contract targets unsupported blends of current and superseded sources without regressing missing-source uncertainty. Evolve explores retrieval filtering, source ranking, and response-construction branches. Each candidate Harness version is evaluated against the pinned benchmark. The current frontier retains the candidates supported by both grounding and uncertainty evidence, while a newly discovered policy conflict becomes an Expert Contribution opportunity.

Related workflows

Task / ImproveStart an Improvement SessionStart from benchmark evidence, prepare a measurable Goal Contract, and choose bounded Work or Evolve behavior.Reference / ImproveGoal ContractsBind an Improvement Session to exact targets, measurable objectives, constraints, and permitted intervention scope.Task / ImproveWork and EvolveChoose bounded implementation work or multi-branch evolutionary search with explicit epoch and provider authorization.Reference / ImproveCandidates and the Current FrontierInterpret candidate stages, canonical receipts, constraints, retained Candidate Systems, and the current frontier.Reference / ImproveChronology, Trajectories, and ReceiptsRead durable session events, safe narrated work segments, evaluation receipts, external handoffs, and usage evidence.Task / Benchmark EvaluationsInspect Evaluation ResultsTrace Dashboard and List signals to Run, Case, Policy, Rubric, completeness, and telemetry evidence.Task / Expert ContributionsRequest an Expert ContributionCreate a focused benchmark contribution with an accountable expert, clear objectives, selected cases, attachments, and appropriate task components.

Related reference pages

Concept / CoevolveCoevolveExplore multiple evidence-backed candidate directions while keeping goals, benchmark receipts, trajectories, and the current frontier connected.Reference / AssetsHarnessesBuild versioned Python Harness bundles, validate and debug Drafts, publish exact Versions, and activate them for benchmark evaluations.Concept / Learning ManualProduct boundariesUnderstand what Teammately owns across correctness specification, benchmark development, evaluation, and improvement.

Source confidence

Code-backed: the active versioned Improve workspace and session contract define starting evidence, Goal Contracts, Work and Evolve behavior, candidates, receipts, chronology, frontiers, and lifecycle controls. Internal coordinator implementation is supporting evidence, not a public API.

Found something unclear?

Report outdated, unsupported, or confusing docs so we can fix the source page.

Report a docs issue

Continue learning

Related docs

Improve Start an Improvement Session Start from benchmark evidence, prepare a measurable Goal Contract, and choose bounded Work or Evolve behavior. Improve Goal Contracts Bind an Improvement Session to exact targets, measurable objectives, constraints, and permitted intervention scope. Improve Work and Evolve Choose bounded implementation work or multi-branch evolutionary search with explicit epoch and provider authorization. Improve Candidates and the Current Frontier Interpret candidate stages, canonical receipts, constraints, retained Candidate Systems, and the current frontier. Improve Chronology, Trajectories, and Receipts Read durable session events, safe narrated work segments, evaluation receipts, external handoffs, and usage evidence. Coevolve Coevolve Explore multiple evidence-backed candidate directions while keeping goals, benchmark receipts, trajectories, and the current frontier connected.
AI context