Observed Signal · Jul 28, 2026 · Technical Release · Source: The Pragmatic Engineer · Impact: 3/5 · Sentiment: Positive
Anthropic's AI Tools Reshape Software Engineering
The Pragmatic Engineer visited Anthropic’s San Francisco lab and interviewed four engineers to describe how improved AI tooling is changing software development. Key examples: the Claude Platform team built and launched Claude Managed Agents after a six-month project and re-architected its platform layer (migrating from Python to Rust); Bun creator Jarred Sumner completed a Zig→Rust rewrite in 11 days using 64 parallel AI agents and about $165,000 in tokens, with substantial verification and testing work after the initial implementation. The article documents shifts in team practices — more agent-driven prototyping, heavy use of automated code review and security scanners, increased fluidity between teams, and continued reliance on planning and PRDs for complex projects.
Demonstrates concrete, production-scale uses of AI agents and AI-driven engineering workflows (fast large codebase migration, managed agent infra, automated review/scanning) that can materially change developer productivity, CI/CD practices, and software architecture decisions.
Track Anthropic Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Anthropic built and launched Claude Managed Agents; the project took around six months and launched in April 2026.
- Anthropic’s Claude Platform is migrating its platform layer from Python to Rust for performance and scalability reasons.
- Jarred Sumner rewrote Bun from Zig to Rust and merged the change in 11 days using 64 parallel AI agents and about $165,000 in tokens; the rewrite shipped to production and powers Claude Code.
- Anthropic teams run many AI agents in parallel (3–10 commonly), use automated AI code review and security scanning (e.g., multiple runs of Claude Security Scanner), and devote most AI usage to verification and testing rather than implementation.
- Anthropic consulted internal sandboxing teams and re-architected Managed Agents to decouple 'brain', 'hands' (sandboxes/tools), and 'session', and implemented a vault + proxy design so credentials are injected only at the egress boundary.
Connected Companies & Entities
7 Entities mapped“Thanks to Anthropic for showing me inside their lab in San Francisco....”
“David Hershey ... working with customers like Cursor, Cognition, and Perplexity...”
“David Hershey ... working with customers like Cursor, Cognition, and Perplexity...”
“David Hershey ... working with customers like Cursor, Cognition, and Perplexity...”
“The project took about six months, by no means a rapid process ... adding support for running agents on AWS, GCP and Azure....”
“Just like before, we had a PRD, it was a Google Doc....”
“The project took about six months, by no means a rapid process ... adding support for running agents on AWS, GCP and Azure....”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Building AI-native Engineering Teams — Anthropic's Fiona Fung
Fiona Fung, Head of Engineering for Claude Code and Cowork at Anthropic, describes how AI is reshaping engineering organization, workflows and productivity. Drawing on 25+ years of engineering experience including 11 years at Microsoft (Visual Studio, TypeScript) and product leadership at Meta (including founding Facebook Marketplace and work on AR glasses and Instagram infrastructure), Fung discusses running teams that now ship substantially more code, which roles AI will transform, specific ways her teams use Claude and Cowork, and managerial changes driven by Claude “routines.” The piece highlights operational gains (Anthropic engineers reportedly ship ~8x more code per quarter versus 2021–2025) and surfaces unresolved challenges such as context-switching and the broader unsolved problems in AI.
AI Agents Transform Software Engineering; Meta Outage Example
The Pragmatic Engineer summarises a Craft Conference keynote arguing that the past six months have brought a step-change in developer workflows due to capable AI agents. The author uses Meta’s recent outage—where a Meta AI bot could change account emails, enabling high-profile takeovers—as a case study linking failures to heavy AI-generated/AI-reviewed code and cuts to integrity/security teams. The piece documents broad adoption of agentic workflows at Anthropic, OpenAI, Google, Uber, startups and large enterprises; cites data from Linear and Cursor showing 2.5–5x productivity increases and larger pull requests; and describes engineering trends and risks: higher individual output, flat team productivity, reduced human review, tooling investments (e.g., Uber’s developer infra), and security/reliability concerns. The article offers guidance for engineers and leaders on adapting to these changes.
Boris Cherny Explains Building Anthropic's Claude Code
Boris Cherny, creator and Head of Claude Code at Anthropic, discusses how Claude Code evolved from a side project into a core internal developer tool and the engineering practices that enable agent-driven development. He describes a high-velocity workflow (running multiple parallel Claude instances to produce many PRs per day), retrieval strategies (simple glob/grep driven by the model outperformed more complex RAG/indexing approaches), and deterministic review and sandboxing patterns used to manage safety. The episode also covers Claude Cowork — a VM-based desktop agent built rapidly to serve non-engineers — and organizational shifts: prototypes replacing PRDs, automation of repetitive code-review comments, and a changing skills profile for engineers as agentic tools handle more of the implementation work.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.