Recorded run / Baseline workflow

success replay

An inspectable recording of the evidence-to-scenario workflow. The plan, specialist calls, returned evidence, evaluation, limitations, and linked digests below come from the verified bundle; they were not reconstructed for presentation.

All recorded runs Inspect source bundle

completed
prototype maturity
fixture evidence
static replay
verified at build

Read this as software evidence, not as live market analysis. The inputs are deterministic fixtures, the planner is rule-based, and the signing key is a disclosed demo key. No production bank data, public inference service, or trained Atticus weights are represented.

Execution trace

Read from top to bottom. Tool activity is visually separated from state transitions; a failed specialist call is marked in text and color.

received
task_received
Task accepted.
planning
plan_created
Created bounded plan with 3 step(s).
planning
policy_decision
Allowed by deterministic catalog policy
planning
policy_decision
Allowed by deterministic catalog policy
planning
policy_decision
Allowed by deterministic catalog policy
executing
tool_started
Invoking atlas.research_snapshot.
executing
tool_completed
Atlas returned 3 point-in-time observations.
executing
tool_started
Invoking fedlens.compare_latest.
executing
tool_completed
Language became less hawkish in the deterministic lexicon.
executing
tool_started
Invoking balancelab.run_scenario.
executing
tool_completed
Synthetic annual NII change: $15.81 million; curve slope change: 50 bps.
evaluating
evaluation_started
Submitting observable trace and evidence to EvalForge.
evaluating
workflow_linked
Linked Atlas, FedLens, BalanceLab, report, and evaluation digests.
completed
task_completed
Workflow finished with EvalForge score 1.000.

Evidence lineage

What each specialist contributed, and the digests that tie the artifacts together.

Specialist artifacts linked to this recorded run
artifact	present	evidence ids	digest
atlas	yes	`atlas-CPI_YOY-2026-06-30` `atlas-UST_2Y-2026-07-24` `atlas-UST_10Y-2026-07-24`	—
balancelab	yes	`balancelab-bear-steepener`	sha256:945d82945e14a…
evaluation	yes	—	sha256:a19025c733ae2…
fedlens	yes	`fedlens-FOMC-2026-06-FIXTURE`	—
report	yes	—	sha256:703662bddbf57…

Evidence

Evidence identifiers carried by the run record.

atlas-CPI_YOY-2026-06-30
atlas-UST_2Y-2026-07-24
atlas-UST_10Y-2026-07-24
fedlens-FOMC-2026-06-FIXTURE
balancelab-bear-steepener

Limitations

Recorded by the run itself, not added afterwards.

Macro, market, and Fed inputs are synthetic fixtures for local development.
BalanceLab uses a simplified educational repricing model, not production bank data.
The deterministic planner stands in for Atticus Core until the model bake-off.
Linked workflow is prototype maturity; signed replay packaging is DRL-019.

Provenance

Build-time verification binds the display to the recorded artifacts. It does not establish a production signing identity.

Recorded execution and integrity metadata
code revision	`drl-019-fixture`
executed at	`2026-07-30T00:00:00+00:00`
configuration	sha256:3ee5e0ff1a697cdcc31e5a87e…
signature	verified at build time

The manifest signature and every artifact digest were verified before this page was generated; an unverified bundle is not rendered at all. The signing key is a demo key, not a production signing identity — treat the signature as structural integrity, not as an attestation of trust.

Compare both runs Research context Repository