Harness Engineering Practices P20. Make Legibility and Calibrated Uncertainty an SLO 🎯 Point Now that generation is cheap, the real bottleneck is "human review time." Diffs should be optimized not just for correctness, but for reviewability. 📝 Overview Optimize diffs for review time, not just correctness. Small, focused PRs. Explanations that tell "why." Explicit flagging of risky areas. Additionally, have the agent explicitly output "areas of low confidence" so the harness can route them to additional verification or human review. Calibrated uncertainty is more valuable than false confidence. 🔍 Explanation As agent generation speed increases, the bottleneck shifts from "writing code" to "reviewing code." Giant PRs, unexplained changes, confidently-presented but actually uncertain implementations — these explosively consume reviewer time. Treating legibility as an SLO (Service Level Objective) and measuring/optimizing PR size, explanation presence, and change rationale improves overall throughput. Having agents explicitly state "I'm not confident here" and "this needs human verification" lets reviewers focus on what matters. This is the most overlooked practice for building trustworthy autonomous agents. 🛠 How to Practice - Add "change rationale," "confidence level (high/medium/low)," and "review focus areas" fields to PR templates and require the agent to fill them - Set PR size limits and force splitting when exceeded - Require "low confidence" markers in agent output so the harness can route those areas to additional verification - Measure review time per PR and identify causes of long reviews (giant diffs, missing explanations, etc.) for improvement 💼 Use Cases - Issue-to-PR agents including change rationale and confidence markers in PRs - Code review agents suppressing low-confidence trivial comments and focusing on types humans miss - Migration: keeping per-unit PRs small and focused to distribute reviewer load ⚠ Pitfalls Over-optimizing for legibility can make agent output overly conservative. "Uncertainty expression" can also become noise — an agent that says "I'm not confident" about everything is useless. Calibration is key: accurately marking only genuinely uncertain areas is what creates value. Don't forget to measure review time either. Quantitatively tracking whether PR spam or giant diffs are crushing review bandwidth is the starting point for improvement. #HarnessEngineering# #CodeReview#

Burning tokens on AI code review? 🔥 This tool turns your codebase into a structural graph so the AI reads only relevant files — cutting tokens by a median of 82x. Title: tirth8205/code-review-graph URL: 🔥 Overview A local-first code intelligence tool that persists a structural map (graph) of your codebase via Tree-sitter parsing. It lets AI assistants review by reading only contextually relevant files instead of the whole repository. ❓ Challenges Solved AI code review tools waste tokens by re-reading large parts of the codebase on every review. ・In large monorepos, context bloats and both cost and latency worsen ・Analyzing change impact required scanning the entire project 💡 Methodology & How It Works A three-stage pipeline. ・Parsing: Tree-sitter builds ASTs, extracting functions, classes, imports, and call relationships ・Graph storage: nodes and edges persist in SQLite (no external database) ・Analysis: on changes, blast-radius analysis traces affected callers, dependents, and tests, returning minimal context It supports many languages, incremental updates under 2 seconds, MCP integration (30 tools), a GitHub Action, and D3.js visualization. 📊 Experimental Results ・Token efficiency: 38x-528x reduction (median ~82x across 6 repos) ・Impact prediction F1 score: 0.71 average ・CLI example: full context 12,921 tokens → graph context 762 tokens (~94% saved) #CodeReview# #AIAgents#

# Claude Code Features and Practical Usage 🚀 Just mention "@/claude" in a PR or issue and watch fixes, features, and reviews happen automatically. Claude Code becomes an AI teammate that works inside your CI. 📌 Title and Feature URL Title: GitHub Actions URL: 📝 Overview Claude Code GitHub Actions integrates Claude Code into your GitHub workflow. Mention "@/claude" on any PR or issue and Claude analyzes your code, creates pull requests, implements features, or fixes bugs. Built on the Claude Agent SDK, it is ideal for automating routine engineering tasks. 🔧 How It Works - It auto-detects whether to run in interactive mode (responding to @/claude mentions) or automation mode (running immediately with a prompt) based on your config. - It respects the repository's CLAUDE.md, following your project standards and existing code patterns. - Code runs on GitHub-hosted runners and uses Sonnet by default (Opus 4.8 can be selected). - Beyond the direct Claude API, it supports Amazon Bedrock and Google Vertex AI. 🛠 Practical Usage - The easiest setup is running "/install-github-app" inside claude in your terminal; it guides you through the GitHub app and secrets (you need repo admin rights). - For manual setup: install the Claude GitHub app ( add ANTHROPIC_API_KEY as a repository secret, and copy examples/claude.yml into .github/workflows/. - Use the action "anthropics/claude-code-action@v1". Pass instructions via "prompt" and CLI arguments via "claude_args". - claude_args examples: --max-turns 5 / --model claude-sonnet-4-6 / --mcp-config /path/to/config.json - Comment examples: "@/claude implement this feature based on the issue description", "@/claude fix the TypeError in the user dashboard component". 🎯 Use Cases - Mention on an issue to auto-create a PR that turns requirements into working code. - Request a standard review on a PR: "@/claude review this for security issues". - Use a schedule (cron) trigger to auto-generate a daily summary of yesterday's commits and open issues. - Wire in the code-review plugin to run its skill automatically on every PR update. ⚠️ Caveats - Never commit API keys directly to the repo; always reference GitHub Secrets (secrets.ANTHROPIC_API_KEY). - Costs accrue both as GitHub Actions minutes and API tokens. Use --max-turns and timeouts to prevent runaway jobs. - If Claude doesn't respond, confirm the comment uses "@/claude" (not "/claude") and that the app and secrets are configured. - v1.0 has breaking changes from beta: remove mode, change direct_prompt to prompt, and move CLI options into claude_args. #ClaudeCode# #CICD#

Codex Code Review can now use custom repository rules in AGENTS.md. Start with a check your reviewers keep repeating. Keep it concise and scoped so Codex can catch repository-specific issues even when the relevant context is siloed.

codex tip: teach code review what your team keeps repeating. add a “Code Review Rules” section to AGENTS.md. codex will apply your repo-specific guidance and cite it on pull requests.

# Learning Palantir Foundry 🚀 Bring complex logic that no-code can't reach into your data platform, along with full software-engineering quality control. That's what Code Repositories delivers. 📌 Title and Feature URL Title: Code Repositories (Python Transforms) URL: 📝 Overview Code Repositories is a web-based integrated development environment (IDE) for creating and collaborating on production-ready code within Foundry. It provides a friendly UI over the underlying Git repositories, so teams can work without command-line access. With platform-specific features, you can apply software development practices directly to data engineering. 🔧 How It Works Version control and collaboration are at its core. - Common Git tasks (branching, committing, release tagging) execute through the web UI - Pull requests drive code review, with "highly configurable" permissions that support quality assurance such as mandatory reviews - IntelliSense, linting, error checking, and contextual help dialogs are available across all repository types - Transforms repositories let you author data transformation logic in Python, Java, or SQL with preview and debugging - Functions repositories natively integrate the Ontology and run low-latency business logic in TypeScript or Python 🛠 Practical Usage - Use PySpark to implement billion-row entity resolution and complex business rules in code - Require PR reviews so a second reviewer and CI checks must pass before merge - Add unit tests to guard transform logic against regressions - In Functions repositories, leverage Ontology-data-type autocomplete to write logic safely - Bring machine learning workflows into the platform via model development repositories 🎯 Use Cases - Implementing complex reconciliation and business rules in PySpark that Pipeline Builder can't express - Structurally eliminating "regressions from editing production directly" through mandatory reviews and branch-based workflows - Implementing derived KPIs and validation logic as Functions reused across apps - Managing ML model training and inference code under governance ⚠️ Caveats - The docs note that Japanese translations are machine-generated and unverified, so localized content may have accuracy limitations - Each repository type (Transforms/Functions/Model) supports different languages and purposes, so pick the one that fits your goal - Being a pro-code environment, the quality benefits only materialize if your organization establishes review, CI, and test practices #PalantirFoundry# #DataEngineering#