# harvey-labs | Harvey | Knowledge Base | Instagit

A benchmark built to evaluate and improve agent capabilities for supporting legal work.

GitHub Stars: 967

Repository: https://github.com/harveyai/harvey-labs

---

## Articles

### [How Reasoning Effort Parameters (Low, Medium, High, Max) Affect Harvey AI Model Behavior](/harveyai/harvey-labs/harvey-ai-reasoning-effort-parameters-model-behavior)

Discover how Harvey AI's reasoning effort parameters (low, medium, high, max) impact model behavior. Improve complex problem-solving by understanding token allocation and latency trade-offs.

- Tags: deep-dive
- Published: 2026-08-11

### [How to Interpret Criterion-Level Results in Harvey-Labs `scores.json`](/harveyai/harvey-labs/harvey-labs-scores-json-criterion-results-reasoning)

Decode harvey-labs scores.json criterion-level results. Understand verdict and reasoning for task pass or fail to gain deep insights into your test outcomes.

- Tags: how-to-guide
- Published: 2026-08-11

### [How Harvey‑Labs Prevents Symlink Escape Attacks During Glob and Grep Operations](/harveyai/harvey-labs/harvey-labs-prevent-symlink-escape-glob-grep)

Discover how Harvey Labs protects against symlink escape attacks in glob and grep operations. Learn how real path resolution secures your sandbox environment.

- Tags: how-to-guide
- Published: 2026-08-11

### [How Harvey-Labs Comparison Dashboards Generate Aggregate Metrics Across Multiple Runs](/harveyai/harvey-labs/harvey-labs-comparison-dashboards-aggregate-metrics)

Discover how Harvey-Labs comparison dashboards aggregate metrics across multiple runs by scanning results, deduplicating, grouping by model, and computing pooled pass rates.

- Tags: internals
- Published: 2026-08-11

### [How Skill Scripts Are Copied Into the Workspace and Made Available to Agents in Harvey-Labs](/harveyai/harvey-labs/harvey-labs-skill-scripts-workspace-availability)

Learn how Harvey-Labs copies skill scripts into a workspace and makes them available to agents for bash execution. Discover the process of exposing scripts via mounted sandbox directories.

- Tags: internals
- Published: 2026-08-11

### [Environment Variables Harvey-Labs Supports and How .env Auto-Loading Works](/harveyai/harvey-labs/harvey-labs-environment-variables-env-loading)

Discover supported environment variables in harvey-labs and understand how .env auto-loading simplifies configuration using python-dotenv for seamless access via os.getenv().

- Tags: how-to-guide
- Published: 2026-08-11

### [Harvey-Labs Document Parsing Pipeline: How AI Agents Extract Text from .docx, .pptx, .xlsx, and .pdf Files](/harveyai/harvey-labs/harvey-labs-document-parsing-pipeline)

Discover the Harvey-Labs document parsing pipeline that uses AI agents to extract text from docx, pptx, xlsx, and pdf files. Learn how it securely handles binary files in an isolated container.

- Tags: how-to-guide
- Published: 2026-08-11

### [How to Configure Custom Shell Command Timeouts in Harvey AI for Long-Running Operations](/harveyai/harvey-labs/custom-shell-command-timeouts-harvey-ai)

Learn how to configure custom shell command timeouts in Harvey AI. Use the CLI flag or Sandbox() to manage long-running operations and prevent infinite loops.

- Tags: how-to-guide
- Published: 2026-08-11

### [How Harvey AI Handles Context Window Overflow and Token Limit Exceedances: 3-Layer Protection System](/harveyai/harvey-labs/harvey-ai-context-window-overflow-token-limits)

Discover how Harvey AI tackles context window overflow with its 3-layer protection system, including token capping, runtime accounting, and graceful failure.

- Tags: deep-dive
- Published: 2026-08-11

### [How All-Pass Rubric Scoring Works in Harvey-Labs: A Complete Technical Guide](/harveyai/harvey-labs/all-pass-rubric-scoring-harvey-labs)

Discover how all-pass rubric scoring in Harvey-Labs works. This guide details the LLM judge's binary pass/fail evaluation for task criteria and its pipeline propagation.

- Tags: deep-dive
- Published: 2026-08-11

### [How to Debug Failed or Incomplete Agent Runs in Harvey-Labs: A Complete Guide to Logs and Output Files](/harveyai/harvey-labs/debug-failed-agent-runs-harvey-labs)

Debug failed Harvey-Labs agent runs by analyzing JSON-L transcripts and output files from ToolExecutor. Master agent loop logs for complete troubleshooting.

- Tags: how-to-guide
- Published: 2026-08-11

### [How Metrics Are Tracked in Harvey-Labs metrics.json and How Document Coverage Is Calculated](/harveyai/harvey-labs/harvey-labs-metrics-json-document-coverage)

Discover how Harvey-Labs tracks run metadata, execution stats, and document coverage in metrics.json. Learn the formula for calculating document coverage.

- Tags: how-to-guide
- Published: 2026-08-11

### [Single-Judge vs Dual-Judge Evaluation Modes in harvey-labs run_eval.py](/harveyai/harvey-labs/single-judge-vs-dual-judge-evaluation-harvey-labs)

Understand single-judge vs dual-judge evaluation modes in harvey-labs run_eval.py. Learn how each mode uses LLMs to score benchmarks and generates different JSON outputs.

- Tags: internals
- Published: 2026-08-11

### [How to Add Custom LLM Model Adapters to Harvey AI: Step-by-Step Guide](/harveyai/harvey-labs/add-custom-llm-adapter-harvey-ai)

Learn how to add custom LLM model adapters to Harvey AI beyond built-in providers. This guide details using the pluggable ModelAdapter abstraction layer for seamless integration. Integrate any LLM provider today.

- Tags: how-to-guide
- Published: 2026-08-11