AI coding agents: writing, reviewing and shipping code
10
Glossary and sources
7 min read · Chapter 10 of 10
Words that mean something else here
| Term | What you'd assume | What it means here |
|---|---|---|
| Agent | One thing | Autocomplete, an editor agent, a terminal agent or a background agent, each with different permissions and risks |
| Harness | A test harness | The code around the model: tools, context, permissions and the loop. Benchmarks score a model and a harness together |
| Memory | The agent learns | Files loaded at the start of a session; nothing persists unless it's written to a file |
| Rules | Policy | Text the model reads and may ignore; permissions and branch protection are the policy |
| Checkpoint | A rollback | Undo for file edits only, not for databases or deployments |
| Sandbox | Isolated | Anything from an operating-system sandbox on a laptop to a virtual machine in a vendor's cloud |
| Verified | Checked by people | SWE-bench Verified was screened by people in 2024 and later found flawed; a "Verified" commit on GitHub is signed, not reviewed |
| Credit | A fixed unit | $0.01 of tokens at GitHub, $0.04 of overage at Kiro, no fixed dollar value on OpenAI's public page |
| Indemnity | Cover for what the agent does | Defence against third-party IP claims on its output |
| Author | Whoever wrote it | A human for copyright; whoever originated the change for PCI; anything an agent sets in git |
| DORA | One thing | Google's software-delivery research program, or the EU's Digital Operational Resilience Act; both concern change management |
What surprised me
Placeholders in your voice, drafted from the research and the earlier guides. Rewrite each with your own moment.
The seat. In spend management a card limit capped what one employee could spend. Here a $19 seat buys a couple of hours of agent time, and everything after that is metered at the lab's price.
The approval. In procure to pay the approver checks an invoice against an order. Here the pull request approval is the only hard gate, and many agent pull requests that fail are never really read.
The supplier. In telco, carriers sold capacity to resellers they competed with. Here a lab can withdraw its models from a rival's coding editor with about 75 days' notice.
Undo. In observability, rolling back a deploy felt like the safety net. An agent's checkpoint undoes file edits, and a deleted database stays deleted.
The issue tracker. In cloud security I thought of permissions as the attack surface. Here a GitHub issue title was enough to get a malicious release published.
Sources
Undated entries were read on October 9, 2026; "search result" means seen only as a search snippet or summary. Company figures are self-reported unless they come from a filing or a regulator, and vendor research measures the vendor's own products or customers.
Agent vendors and labs: documentation, pricing and terms
- GitHub: Copilot cloud agent, cloud agent risks and mitigations, Copilot plans, moving to usage-based billing (Apr 2026), pausing Business signups (Apr 2026, search result), reopening signups (Sep 2026, search result), Claude and Codex on Agent HQ (Feb 2026, search result), Secret Protection and Code Security (Mar 2025), code referencing and indemnity, establishing trust in Copilot, npm classic tokens revoked (Dec 2025), Copilot features (Oct 2026), Copilot data residency and FedRAMP (Apr 2026), FedRAMP models (search result)
- Anthropic: how Claude Code works, agent teams, costs, data usage, sandboxing (search result), plans, API pricing, commercial terms (effective Jun 2025), Claude for Startups (Oct 2026), Claude Marketplace (Oct 2026), Claude Code for government (Jul 2026, search result)
- OpenAI: Codex cloud, Codex pricing, data usage, harness engineering (Feb 2026, search result), Codex Security (Mar 2026)
- Google: Jules, Gemini Code Assist, privacy notice for individuals, Code Assist FAQ
- AWS: Kiro pricing, Kiro specs, Q Developer IDE end of support (search result), Q Developer service improvement, AWS Transform (search result), Claude for Enterprise in AWS Marketplace (Oct 2025)
- Cursor: pricing, pricing documentation, cloud agents, Bugbot, semantic search blog (Nov 2025, search result), terms of service (Sep 2026), MSA (Aug 2026), data use (Sep 2026), enterprise (Oct 2026)
- Cognition: Devin pricing, Devin introduction
- Startup programs: TechRadar, AWS Activate credits for third-party Bedrock models (search result); GitHub for Startups (aggregator, search result); OpenAI for Startups (aggregator, search result)
- Mistral: pricing (search result); Hyscaler, GLM coding plan (2026, search result)
- App builders and review: Replit pricing, Lovable pricing, CodeRabbit pricing
- Standards and tooling: AGENTS.md, pnpm settings, Linux kernel policy on coding assistants (Dec 2025)
- Production feedback: Sentry, Seer (search result); Dynatrace Hub, Bluebox (Oct 2026)
Company disclosures
- Microsoft: FY26 Q4 earnings (Jul 2026)
- Alphabet: Q2 2026 CEO remarks (Jul 2026)
- Anthropic: Series G and Claude Code run-rate (Feb 2026), higher limits and SpaceX compute (May 2026), acquires Bun (Dec 2025, search result)
- SpaceX: S-1/A (2026, search result)
- GitLab: Q4 FY26 results (Mar 2026, search result)
Market, deals and pricing changes (press)
- Cursor and SpaceX: CNBC, SpaceX to acquire Cursor (Jun 2026, search result); Techzine, SpaceX completes Cursor (Aug 2026); Dealroom, Cursor tops $4B (Jun 2026, search result); TechCrunch, Cursor's $50B talks and margins (Apr 2026); eWeek, Cursor Origin (Aug 2026)
- OpenAI and Cursor: TNW, OpenAI ends Cursor contract (Aug 2026); Crypto Briefing, 5% of traffic (search result); The New Stack, Anthropic sticks with Cursor (headline only)
- Windsurf: TechCrunch, Anthropic cuts Windsurf's access (Jun 2025, search result); Bloomberg Law, OpenAI agrees to buy Windsurf (May 2025, search result); Maginative, Cognition acquires Windsurf (Jul 2025, search result)
- Pricing changes: TechCrunch, Cursor apologizes (Jul 2025, search result); Simon Willison, Anthropic's weekly limits (Jul 2025, search result); VentureBeat, Anthropic and third-party harnesses (2026, search result); Visual Studio Magazine, Copilot billing shock (Jun 2026, search result); Pragmatic Engineer, token spend breaks budgets (Apr 2026)
- Margins: TechCrunch, high costs and thin margins (Aug 2025); The Information, coding margins (Aug 2025, search result)
- Claude Marketplace: SiliconANGLE, Anthropic launches Claude Marketplace (Mar 2026, search result)
- Labs: Constellation Research, Codex at 5 million weekly users (Jun 2026, search result); TNW, OpenAI acquires Ona (Jun 2026, search result); Fortune, Anthropic's draft S-1 (Sep 2026); TNW, Nvidia and Poolside (Aug 2026, search result)
- App layer: Value Add VC, Cognition at $48B (Sep 2026, search result); Orca Router, SWE-2 (Sep 2026, search result); Dealroom, Lovable at $13.3B (Aug 2026, search result); Trending Topics, Replit at $9B (Mar 2026, search result); Sacra, Bolt (search result)
- Review and security: TechCrunch, CodeRabbit raises $60M (Sep 2025); Hyrax, CodeRabbit's Series C (Aug 2026, search result); SiliconANGLE, Cursor acquires Graphite (Dec 2025); BankInfoSecurity, Snyk cuts 90 jobs (Jun 2026); SiliconANGLE, Semgrep Series D (Feb 2025); BankInfoSecurity, Socket raises $60M (May 2026); SiliconANGLE, Aikido Series B (Jan 2026); Hackmag, Claude Code Security (Feb 2026); Datamation, Google CodeMender (Oct 2025); Help Net Security, Mandiant's vulnerability discovery tool (Aug 2026); TechCrunch, Moderne and OpenRewrite (Feb 2025, search result)
Surveys of developers and buyers
- The Pragmatic Engineer, AI tooling 2026 (Feb-Mar 2026)
- JetBrains Research, which AI coding tools developers use at work (Apr 2026, January data) and AI coding agent adoption 2026 (Aug 2026)
- Stack Overflow, results of the 2026 Developer Survey (Oct 2026) and agents on a leash (May 2026)
- Menlo Ventures' 2025 enterprise AI report, as covered by No Jitter, $19 billion of generative AI spend (Dec 2025, search result), and SaaStr, 55% of departmental AI spend on coding (search result)
Research, benchmarks and outcomes
- METR: early-2025 study of experienced developers (Jul 2025), uplift update (Feb 2026), research index (Oct 2026), time horizons (search result)
- DORA: AI research (Oct 2026), 2025 report (Sep 2025)
- Cui, Demirer and colleagues, field experiments with Copilot (2024); Xu and colleagues, Copilot in open source (Oct 2025)
- Agent pull requests: Mazloomzadeh, Morovati and Khomh, agentic pull requests (Jul 2026); Ehsani and colleagues, failed agentic pull requests (Jan 2026); Yoshioka and colleagues, review activity and merges (2026, search result); rejected agentic pull requests (May 2026, search result); Raida and Hou, early adoption of agentic tools (Jul 2026)
- Context and environment: Gloaguen and colleagues, evaluating AGENTS.md (Feb 2026)
- Benchmarks: The Decoder, OpenAI retires SWE-bench Verified (Feb 2026) and 30% of SWE-bench Pro broken (Jul 2026); ImpossibleBench (Oct 2025)
- Company reports: Stripe, Minions (2026); Spotify, background coding agent (Nov 2025); Google, migrations with LLMs (Jan 2025); Semafor, Google's 75% (Apr 2026); Fortune, Anthropic's 80% (Jun 2026); OpenAI, the shift to agentic AI (Jun 2026); TechRadar, Microsoft's 20-30% (Apr 2025); Quartz, Goldman Sachs and Devin (Jul 2025, search result); NBC Chicago, Goldman pilots an autonomous coder (Jul 2025, search result)
- Amazon's sign-off rule: The Decoder, senior engineers as the filter (Mar 2026); CIO, Amazon links outages to AI efforts (Mar 2026)
- Security of generated code: Veracode, 2026 GenAI code security report (Jul 2026, vendor); SusVibes (2026); Cloud Security Alliance, package hallucinations (Apr 2026); GitGuardian, State of Secrets Sprawl 2026 (Mar 2026, vendor)
Law, regulators and standards
- Copyright: US Copyright Office, Part 2 report (Jan 2025); SCOTUSblog, Thaler v. Perlmutter (Mar 2026); Gibson Dunn, Doe v. GitHub (Sep 2026)
- Training defaults: heise, GitHub to train on user data with opt-out (2026)
- Change control: PCI Security Standards Council, AI principles (Sep 2025); PCI DSS 6.2.3.1 (mirror); Advisera, EU DORA RTS Article 17; Cloud Security Alliance, SOC 2 and AI controls (Aug 2026); Cimcon, SR 26-2 and AI agents (2026); Baker McKenzie, MAS agentic AI safeguards (Jul 2026)
- EU product rules: Jones Day, Cyber Resilience Act reporting (Jul 2026)
Incidents, attacks and supply chain
- Deleted data: The Register, Replit's response (Jul 2025); AI Incident Database, Gemini CLI (2025); TechRadar, Antigravity deletes a drive (Dec 2025); GIGAZINE, Claude Code deletes a home folder (Dec 2025); Computing, an AI coding agent goes rogue (Apr 2026); GeekWire, Amazon pushes back on the FT (Feb 2026)
- Attacks on agents: GitGuardian, inside the Nx credential leak (2025, vendor); CSO Online, AI in CI/CD pipelines (Dec 2025); Simon Willison, Clinejection (Mar 2026); The Register, CamoLeak (Oct 2025)
- Poisoned tooling in CI: CSO Online, CERT-EU on Trivy (2026); ITPro, LiteLLM on PyPI (Mar 2026)
Field Guides are learning notes, not legal or compliance advice. Rules and fees change; check the cited primary sources before you act on anything here.