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/ablations.py
agentworkbench/active_learning.py
agentworkbench/aggregate_metrics.py
agentworkbench/analysis_helpers.py
agentworkbench/artifacts.py
agentworkbench/audits.py
agentworkbench/bayesian.py
agentworkbench/behavior_summary.py
agentworkbench/benchmark_ingestion.py
agentworkbench/benchmark_quality.py
agentworkbench/benchmarks.py
agentworkbench/briefs.py
agentworkbench/builders.py
agentworkbench/case_selection.py
agentworkbench/chain.py
agentworkbench/cleanup.py
agentworkbench/cli.py
agentworkbench/compare_statistics.py
agentworkbench/config.py
agentworkbench/constants.py
agentworkbench/demo_helpers.py
agentworkbench/discovery.py
agentworkbench/errors.py
agentworkbench/evals.py
agentworkbench/evidence.py
agentworkbench/execution_scheduler.py
agentworkbench/experiment_analysis.py
agentworkbench/experiment_paths.py
agentworkbench/factorial.py
agentworkbench/human_integration.py
agentworkbench/human_review.py
agentworkbench/human_review_store.py
agentworkbench/instrumentation.py
agentworkbench/iterate.py
agentworkbench/learned_scorer.py
agentworkbench/loop_checks.py
agentworkbench/matrix.py
agentworkbench/models.py
agentworkbench/multiturn.py
agentworkbench/next_steps.py
agentworkbench/optimization_utils.py
agentworkbench/optimize.py
agentworkbench/patches.py
agentworkbench/pricing.py
agentworkbench/proposals.py
agentworkbench/redteam.py
agentworkbench/release.py
agentworkbench/report_builder.py
agentworkbench/report_compare.py
agentworkbench/report_diagnosis.py
agentworkbench/report_experiment.py
agentworkbench/report_next.py
agentworkbench/report_scorer_audit.py
agentworkbench/report_status.py
agentworkbench/reports.py
agentworkbench/review_html.py
agentworkbench/route_policy.py
agentworkbench/route_policy_authoring.py
agentworkbench/route_policy_templates.py
agentworkbench/run_context.py
agentworkbench/run_failures.py
agentworkbench/run_finalize.py
agentworkbench/run_helpers.py
agentworkbench/run_rows.py
agentworkbench/runner.py
agentworkbench/runner_compare.py
agentworkbench/runner_diagnosis.py
agentworkbench/safe_expressions.py
agentworkbench/scaffold.py
agentworkbench/scorer_audit.py
agentworkbench/scorer_authoring.py
agentworkbench/scorer_utils.py
agentworkbench/sdk.py
agentworkbench/simple.py
agentworkbench/snapshot.py
agentworkbench/stability.py
agentworkbench/stability_utils.py
agentworkbench/surface_details.py
agentworkbench/surface_recommendations.py
agentworkbench/surface_usage.py
agentworkbench/telemetry.py
agentworkbench/text_utils.py
agentworkbench/thresholds.py
agentworkbench/tool_interfaces.py
agentworkbench/tracing.py
agentworkbench/utils.py
agentworkbench/workflow.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/adapters/__init__.py
agentworkbench/adapters/command.py
agentworkbench/adapters/common.py
agentworkbench/adapters/provider.py
agentworkbench/adapters/python.py
agentworkbench/adapters/shared.py
agentworkbench/benchmarks_vision/__init__.py
agentworkbench/benchmarks_vision/templates.py
agentworkbench/extensions/__init__.py
agentworkbench/extensions/base.py
agentworkbench/extensions/loader.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/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/review/__init__.py
agentworkbench/review/cards.py
agentworkbench/review/common.py
agentworkbench/review/compare.py
agentworkbench/review/summary.py
agentworkbench/review/telemetry.py
agentworkbench/review/terminal.py
agentworkbench/runners/__init__.py
agentworkbench/runners/multiturn.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/vision.py
agentworkbench/scorers/workflow.py
completions/_awb
completions/awb.bash
docs/IMPROVEMENT_PLANS_README.md
docs/api_reference.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/route_policy.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
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_audits.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_human_review.py
tests/test_instrumentation_drift.py
tests/test_live_agent_demo.py
tests/test_loop_checks.py
tests/test_multi_agent_workflows.py
tests/test_multimodal_support.py
tests/test_multiturn.py
tests/test_openai_compatible_transport.py
tests/test_package.py
tests/test_provider_adapter.py
tests/test_release_quality_modules.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