1Password runs Codex from spec to production investigation, injecting credentials at the point of tool calls via secret references so plaintext secrets never enter the model context
1Password's engineers hand Codex well-defined user stories, which it breaks into functional specs and near-final prototypes for systems engineers to finish; Codex also reviews PRs before a human, runs acceptance tests in parallel worktrees, and investigates production issues by pulling evidence from incident management, telemetry, source control, paging and feature flags. Security is enforced by keeping secret references (not credentials) in repos and resolving them only when Codex calls an approved internal tool, plus AppSec policies packaged as reusable skills. OpenAI reports a 20.9% measured productivity improvement for the core cohort, a 10.9% cut in median PR cycle time, and investigation of a defect spanning 10+ microservices falling from about two hours to 5-20 minutes. 1Password's 553% ROI and ~$784K annual capacity value are modeled estimates (50 developers, $250K loaded cost, 40% 'directional' Codex attribution, 75% realization) (reported by OpenAI, citing 1Password)
Handoffs between planning, implementation and review slowed delivery, while any AI tooling had to meet a zero-knowledge security posture around credentials (reported by OpenAI)
Engineer gives Codex a user story and the intended user experience
Codex produces functional specs, dependency checks and a near-final prototype
Codex reviews PRs before human review and runs acceptance tests in parallel worktrees
When Codex calls approved internal tools, 1Password resolves secret references and injects credentials at the point of action
For incidents, Codex pulls evidence from incident management, telemetry, source control, paging and feature flags; engineers decide fixes
Human-in-the-loop: Engineers define stories, finish backend integration, perform human PR review after Codex's first pass and decide incident remediation.
20.9% engineering productivity improvement for the core Codex cohort and 10.9% lower median PR cycle time Reported by OpenAI, citing 1Password; productivity metric definition not given · Source (openai.com)
Investigation of a defect spanning 10+ microservices cut from ~2 hours to 5-20 minutes Reported by OpenAI; single incident · Source (openai.com)
Estimated 553% ROI and ~$784K annual capacity value - a model-based projection using assumed attribution and realization rates, not realized savings Reported by OpenAI, citing 1Password · Source (openai.com)
When Codex calls an approved internal tool, 1Password resolves and injects the credential at the point of action, so the plaintext value never enters the model context.
Modeled annual engineering capacity value: $783,750, based on 50 consistently active Codex developers, a $250,000 fully loaded annual cost per developer, 20.9% measured productivity improvement, 40% directional Codex attribution, and 75% realization of productive capacity.
Vendor's own product: Microsoft's .NET team reports ten months (May 2025-March 2026) of using GitHub Copilot coding agent (CCA) in dotnet/runtime, the repository behind the .NET runtime, JIT, GC and core libraries. Maintainers explicitly assign bounded tasks; CCA works in a sandbox and opens a PR, and every PR, whether from CCA, staff or the community, also gets automatic Copilot Code Review. Early runs failed because the repo had no copilot-instructions file and the sandbox firewall blocked the NuGet feeds the build needs; the team added instructions and access first. Microsoft reports 878 CCA PRs (14% of all PRs), 535 merged, a 67.9% success rate versus 87.1% for Microsoft engineers' PRs, and 3 of 535 merged CCA PRs reverted (0.6%) versus 0.8% for other PRs (reported by Microsoft; the post says the data is directional, since tasks given to CCA were hand-picked and more bounded)
AgentMail's AgentID gives agents email-based identities tied to a human owner so services like Context.dev can allow autonomous agent signups without fraud.
AMD uses GitHub Copilot coding agent to auto-triage 1M+ nightly simulation failures, propose fixes for morning review, and Autofix to resolve ~70% of vulnerability classes automatically, compressing feature cycles from weeks to days across 20,000+ engineers on GitHub Enterprise (reported by GitHub / AMD)
The ERP platform planning team at Korean beauty group AMOREPACIFIC (Sulwhasoo, Laneige and others) ran an August 2025-March 2026 project with AWS to bring AI-driven development to its SAP ECC 6.0 (NetWeaver 7.40) estate, where ABAP lives inside the SAP server and the SAPUI5 front end uses a custom NWDI portal framework. The team chose Kiro IDE: in Spec mode the agent turns a Jira ticket and FS/TS documents into requirements, design and task specs and then generates ABAP/SAPUI5 code; Vibe mode handles chat-driven changes to existing modules. An SAP MCP server built by AWS solutions architects gives the agent read access to RFC functions and table structures, and 'steering' files encode in-house coding conventions; developers review the generated code. Across four projects (one ABAP, three SAPUI5), the team reports productivity gains of up to 72% against an earlier 20-30% estimate for generic tools, and documentation time cut by 80% (reported on AWS's Korean tech blog; 'up to' figures from internal analysis over four projects)