AGENTS.md
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
SECURITY.md
pyproject.toml
agentworkbench/__init__.py
agentworkbench/__main__.py
agentworkbench/artifacts.py
agentworkbench/cleanup.py
agentworkbench/config.py
agentworkbench/constants.py
agentworkbench/errors.py
agentworkbench/models.py
agentworkbench/multiturn.py
agentworkbench/simple.py
agentworkbench.egg-info/PKG-INFO
agentworkbench.egg-info/SOURCES.txt
agentworkbench.egg-info/dependency_links.txt
agentworkbench.egg-info/entry_points.txt
agentworkbench.egg-info/requires.txt
agentworkbench.egg-info/top_level.txt
agentworkbench/_compat/__init__.py
agentworkbench/adapters/__init__.py
agentworkbench/adapters/command.py
agentworkbench/adapters/common.py
agentworkbench/adapters/provider.py
agentworkbench/adapters/python.py
agentworkbench/adapters/shared.py
agentworkbench/assurance/__init__.py
agentworkbench/assurance/report.py
agentworkbench/audit/__init__.py
agentworkbench/audit/audits.py
agentworkbench/audit/scorer_audit.py
agentworkbench/audit/scorer_authoring.py
agentworkbench/benchmarks/__init__.py
agentworkbench/benchmarks/aggregate_metrics.py
agentworkbench/benchmarks/behavior_summary.py
agentworkbench/benchmarks/benchmarks.py
agentworkbench/benchmarks/ingestion.py
agentworkbench/benchmarks/quality.py
agentworkbench/benchmarks/vision/__init__.py
agentworkbench/benchmarks/vision/templates.py
agentworkbench/briefs/__init__.py
agentworkbench/briefs/brief.py
agentworkbench/briefs/drafting.py
agentworkbench/briefs/finalization.py
agentworkbench/briefs/lifecycle.py
agentworkbench/chains/__init__.py
agentworkbench/chains/execution.py
agentworkbench/chains/spec.py
agentworkbench/cli/__init__.py
agentworkbench/cli/coding_agent.py
agentworkbench/cli/main.py
agentworkbench/cli/commands/__init__.py
agentworkbench/cli/commands/artifacts.py
agentworkbench/cli/commands/benchmarks.py
agentworkbench/cli/commands/coding_agent.py
agentworkbench/cli/commands/dialogue.py
agentworkbench/cli/commands/improve.py
agentworkbench/cli/commands/quick.py
agentworkbench/cli/commands/review_ops.py
agentworkbench/coding_agent/__init__.py
agentworkbench/coding_agent/integration.py
agentworkbench/core/__init__.py
agentworkbench/core/config.py
agentworkbench/core/constants.py
agentworkbench/core/errors.py
agentworkbench/core/evidence.py
agentworkbench/core/models.py
agentworkbench/core/thresholds.py
agentworkbench/evals/__init__.py
agentworkbench/evals/cases.py
agentworkbench/evals/generation.py
agentworkbench/evals/management.py
agentworkbench/evals/suite.py
agentworkbench/evals/scorers/__init__.py
agentworkbench/experiments/__init__.py
agentworkbench/experiments/aggregation.py
agentworkbench/experiments/analysis.py
agentworkbench/experiments/analysis_helpers.py
agentworkbench/experiments/compare.py
agentworkbench/experiments/diagnosis.py
agentworkbench/experiments/gates.py
agentworkbench/experiments/paths.py
agentworkbench/experiments/statistics.py
agentworkbench/human/__init__.py
agentworkbench/human/checkpoints.py
agentworkbench/human/integration.py
agentworkbench/human/review.py
agentworkbench/human/review_store.py
agentworkbench/instrumentation/__init__.py
agentworkbench/instrumentation/base.py
agentworkbench/instrumentation/command_runtime.py
agentworkbench/instrumentation/common.py
agentworkbench/instrumentation/provider_runtime.py
agentworkbench/instrumentation/python_runtime.py
agentworkbench/loop/__init__.py
agentworkbench/loop/checks.py
agentworkbench/optimization/__init__.py
agentworkbench/optimization/ablations.py
agentworkbench/optimization/active_learning.py
agentworkbench/optimization/bayesian.py
agentworkbench/optimization/factorial.py
agentworkbench/optimization/iteration.py
agentworkbench/optimization/matrix.py
agentworkbench/optimization/optimize.py
agentworkbench/optimization/patches.py
agentworkbench/optimization/proposals.py
agentworkbench/optimization/utils.py
agentworkbench/providers/__init__.py
agentworkbench/providers/base.py
agentworkbench/providers/openai_compatible.py
agentworkbench/providers/pricing_resolver.py
agentworkbench/providers/replay_cache.py
agentworkbench/providers/streaming.py
agentworkbench/redteam/__init__.py
agentworkbench/redteam/redteam.py
agentworkbench/reports/__init__.py
agentworkbench/reports/builder.py
agentworkbench/reports/compare.py
agentworkbench/reports/diagnosis.py
agentworkbench/reports/experiment.py
agentworkbench/reports/generator.py
agentworkbench/reports/next.py
agentworkbench/reports/renderers.py
agentworkbench/reports/scorer_audit.py
agentworkbench/reports/status.py
agentworkbench/runners/__init__.py
agentworkbench/runners/base.py
agentworkbench/runners/batch.py
agentworkbench/runners/chain.py
agentworkbench/runners/context.py
agentworkbench/runners/experiment.py
agentworkbench/runners/failures.py
agentworkbench/runners/finalize.py
agentworkbench/runners/helpers.py
agentworkbench/runners/multiturn.py
agentworkbench/runners/rows.py
agentworkbench/runners/single.py
agentworkbench/runners/workflow.py
agentworkbench/scheduler/__init__.py
agentworkbench/scheduler/scheduler.py
agentworkbench/scorers/__init__.py
agentworkbench/scorers/artifacts.py
agentworkbench/scorers/audit.py
agentworkbench/scorers/grounding.py
agentworkbench/scorers/json_schema.py
agentworkbench/scorers/judge.py
agentworkbench/scorers/multiturn.py
agentworkbench/scorers/output_quality.py
agentworkbench/scorers/presets.py
agentworkbench/scorers/process_alignment.py
agentworkbench/scorers/safety.py
agentworkbench/scorers/utils.py
agentworkbench/scorers/vision.py
agentworkbench/scorers/workflow.py
agentworkbench/sdk/__init__.py
agentworkbench/sdk/builders.py
agentworkbench/sdk/demo_helpers.py
agentworkbench/sdk/scaffold.py
agentworkbench/sdk/simple.py
agentworkbench/surfaces/__init__.py
agentworkbench/surfaces/details.py
agentworkbench/surfaces/discovery.py
agentworkbench/surfaces/recommendations.py
agentworkbench/surfaces/tool_interfaces.py
agentworkbench/surfaces/usage.py
agentworkbench/telemetry/__init__.py
agentworkbench/telemetry/events.py
agentworkbench/telemetry/telemetry.py
agentworkbench/telemetry/tracing.py
agentworkbench/utils/__init__.py
agentworkbench/utils/case_selection.py
agentworkbench/utils/learned_scorer.py
agentworkbench/utils/pricing.py
agentworkbench/utils/safe_expressions.py
agentworkbench/utils/serialization.py
agentworkbench/utils/snapshots.py
agentworkbench/utils/stability.py
agentworkbench/utils/text.py
agentworkbench/workflows/__init__.py
agentworkbench/workflows/execution.py
agentworkbench/workflows/policy_authoring.py
agentworkbench/workflows/policy_templates.py
agentworkbench/workflows/routing.py
agentworkbench/workflows/spec.py
completions/_awb
completions/awb.bash
docs/IMPROVEMENT_PLANS_README.md
docs/README.md
docs/adaptation_surfaces.md
docs/api_reference.md
docs/assurance.md
docs/cli_reference.md
docs/codebase_map.md
docs/codex_agent_guide.md
docs/general_improvements_roadmap.md
docs/implementation_checklist.md
docs/improvement_plan_executive_summary.md
docs/limitations.md
docs/master_improvement_plan.md
docs/multi_turn_and_chains.md
docs/operational_hardening_todo.md
docs/quickstart.md
docs/recipes.md
docs/release_and_laptop_setup.md
docs/release_dogfood.md
docs/restructure_migration.md
docs/route_policy.md
docs/troubleshooting.md
docs/vision_agent_guide.md
docs/vision_multimodal_roadmap.md
docs/concepts/agents.md
docs/concepts/benchmarks.md
docs/concepts/experiments.md
docs/concepts/scorers.md
docs/contracts/README.md
docs/contracts/media_attachments.md
docs/contracts/release_evidence.md
docs/contracts/run_artifacts.md
docs/contracts/score_results.md
docs/contracts/trace_and_evidence.md
examples/live-agent-demo/.gitignore
examples/live-agent-demo/README.md
examples/live-agent-demo/TARGET_AGENT.md
examples/live-agent-demo/.agent-workbench/workbench.yaml
examples/live-agent-demo/.agent-workbench/agents/live-support-baseline.yaml
examples/live-agent-demo/.agent-workbench/agents/live-support-candidate-python.yaml
examples/live-agent-demo/.agent-workbench/agents/live-support-candidate.yaml
examples/live-agent-demo/.agent-workbench/briefs/live-support-agent.yaml
examples/live-agent-demo/.agent-workbench/discovery/repo-brief.md
examples/live-agent-demo/.agent-workbench/discovery/repo-summary.json
examples/live-agent-demo/.agent-workbench/evals/live-support-agent.jsonl
examples/live-agent-demo/.agent-workbench/evals/live-support-agent.splits.yaml
examples/live-agent-demo/.agent-workbench/evals/live-support-agent.suite.yaml
examples/live-agent-demo/.agent-workbench/scorers/live-support-agent_default.py
examples/live-agent-demo/target_agent/__init__.py
examples/live-agent-demo/target_agent/cli.py
examples/live-agent-demo/target_agent/memory.py
examples/live-agent-demo/target_agent/runtime.py
examples/live-agent-demo/target_agent/tools.py
examples/live-agent-demo/target_agent/prompts/reviewer.md
examples/live-agent-demo/target_agent/prompts/system.md
examples/live-provider-demo/.gitignore
examples/live-provider-demo/README.md
examples/live-provider-demo/TARGET_AGENT.md
examples/live-provider-demo/.agent-workbench/workbench.yaml
examples/live-provider-demo/.agent-workbench/agents/cerebras-support-bloated.yaml
examples/live-provider-demo/.agent-workbench/agents/cerebras-support-pruned.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-release-no-risk-review.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-release-workflow.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-router-no-history.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-router-workflow.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-support-baseline.yaml
examples/live-provider-demo/.agent-workbench/agents/groq-support-grounded.yaml
examples/live-provider-demo/.agent-workbench/briefs/escalation-router-agent.yaml
examples/live-provider-demo/.agent-workbench/briefs/release-gate-agent.yaml
examples/live-provider-demo/.agent-workbench/briefs/support-ops-agent.packet.md
examples/live-provider-demo/.agent-workbench/briefs/support-ops-agent.yaml
examples/live-provider-demo/.agent-workbench/discovery/repo-brief.md
examples/live-provider-demo/.agent-workbench/discovery/repo-summary.json
examples/live-provider-demo/.agent-workbench/evals/escalation-router-agent.jsonl
examples/live-provider-demo/.agent-workbench/evals/escalation-router-agent.splits.yaml
examples/live-provider-demo/.agent-workbench/evals/escalation-router-agent.suite.yaml
examples/live-provider-demo/.agent-workbench/evals/release-gate-agent.jsonl
examples/live-provider-demo/.agent-workbench/evals/release-gate-agent.splits.yaml
examples/live-provider-demo/.agent-workbench/evals/release-gate-agent.suite.yaml
examples/live-provider-demo/.agent-workbench/evals/support-ops-agent.jsonl
examples/live-provider-demo/.agent-workbench/evals/support-ops-agent.splits.yaml
examples/live-provider-demo/.agent-workbench/evals/support-ops-agent.suite.yaml
examples/live-provider-demo/.agent-workbench/scorers/escalation-router-agent_default.py
examples/live-provider-demo/.agent-workbench/scorers/release-gate-agent_default.py
examples/live-provider-demo/.agent-workbench/scorers/support-ops-agent_default.py
examples/live-provider-demo/knowledge/incidents.md
examples/live-provider-demo/knowledge/launch-calendar.md
examples/live-provider-demo/knowledge/refunds.md
examples/live-provider-demo/knowledge/release-checklist.md
examples/live-provider-demo/knowledge/routing.md
examples/live-provider-demo/knowledge/style.md
examples/live-provider-demo/knowledge/team-directory.md
examples/live-provider-demo/knowledge/customer-notes/acme-vip.md
examples/live-provider-demo/knowledge/customer-notes/zenith-enterprise.md
examples/live-provider-demo/target_agent/__init__.py
examples/live-provider-demo/target_agent/cli.py
examples/live-provider-demo/target_agent/memory.py
examples/live-provider-demo/target_agent/runtime.py
examples/live-provider-demo/target_agent/tools.py
examples/live-provider-demo/target_agent/prompts/release_reviewer.md
examples/live-provider-demo/target_agent/prompts/release_system.md
examples/live-provider-demo/target_agent/prompts/reviewer.md
examples/live-provider-demo/target_agent/prompts/router_reviewer.md
examples/live-provider-demo/target_agent/prompts/router_system.md
examples/live-provider-demo/target_agent/prompts/system.md
examples/minimum-viable-agent/README.md
examples/minimum-viable-agent/.agent-workbench/agents/mva-agent.yaml
examples/minimum-viable-agent/.agent-workbench/evals/mva-eval.jsonl
examples/minimum-viable-agent/target_agent/__init__.py
examples/minimum-viable-agent/target_agent/cli.py
examples/minimum-viable-agent/target_agent/runtime.py
examples/vision-agent-demo/README.md
tests/test_artifact_cleanup.py
tests/test_chain_workflow_helpers.py
tests/test_cli.py
tests/test_discovery.py
tests/test_evidence.py
tests/test_example_runtime_events.py
tests/test_instrumentation_drift.py
tests/test_live_agent_demo.py
tests/test_loop_checks.py
tests/test_multimodal_support.py
tests/test_openai_compatible_transport.py
tests/test_package.py
tests/test_provider_adapter.py
tests/test_release_quality_modules.py
tests/test_restructured_imports.py
tests/test_route_policy.py
tests/test_safe_expressions.py
tests/test_scorer_utils.py
tests/test_simple_api.py
tests/test_snapshot.py
tests/test_streaming.py
tests/test_surface_coverage_gates.py
tests/test_surface_recommendations.py
tests/test_telemetry_fixtures.py
tests/test_tool_interface_surfaces.py
tests/test_tracing.py
tests/test_vision_scorers.py
tests/test_workflow_regressions.py