# Anthropic, OpenAI & Thoughtworks on Context Engineering

## Executive summary

The core challenge in deploying AI agents is shifting from model intelligence to context engineering. Speakers from Anthropic, OpenAI, Thoughtworks, and Tessl argue that the surrounding context—including organizational knowledge, structured guides, and robust feedback loops—is the primary multiplier for agent capability. Key technical concepts include defining new constraints (human time, attention, context window), building specialized harnesses using computational tools like codemods and static analysis, and establishing a Context Development Lifecycle (CDLC) that runs parallel to the traditional Software Development Lifecycle (SDLC).

## Key takeaways

- Context Engineering Multiplies Intelligence: Model intelligence alone is insufficient for durable, scalable products. Context engineering provides the necessary domain-specific knowledge required for agents to succeed within an organization.
- Remaining Software Constraints: Most traditional software engineering constraints are obsolete. The three remaining foundational limits when using human-agent teams are: human time (the most scarce resource), human/model attention, and the context window size.
- Agent Harness Architecture: A coding agent harness requires two components: 'guides' that proactively point the agent forward, and 'sensors' that provide immediate feedback for self-correction (e.g., static analysis, logs).
- The Context Development Lifecycle (CDLC): Humans must own the CDLC while agents handle the SDLC. This involves generating context, evaluating agent performance via runtime observability, and optimizing skills in a continuous loop.

## Technical details

- Context Engineering: Context engineering is identified as the main lever for translating raw model intelligence into durable, scalable products. It involves distilling useful primitives and managing memory to support continual learning paradigms like 'dreaming'.
- LLM Constraints & Attention: The foundational limits on agent performance include human time (a scarce resource), attention capacity (both human and model, as attention must sum to one), and the context window. Overcoming these requires retooling workflows for parallel task execution.
- Agent Harness Components: Harnesses are built using computational guides (e.g., codemods like OpenRewrite, effective code search) and sensors (e.g., static analysis, log access). Codemods are highlighted as powerful tools for version upgrades and framework migrations.
- Observability & Evaluation: Runtime observability is crucial for monitoring coding agents to extract real-world evaluation scenarios and identify gaps. This data can then be used to update and optimize agent skills, driving the CDLC.

## Practical implications

- Organizations must shift focus from improving model intelligence to optimizing the context surrounding the models.
- Implementing a Context Development Lifecycle (CDLC) alongside the SDLC is necessary for scalable agent deployment.
- Utilizing computational tools like codemods and static analysis within agent harnesses significantly increases the probability of successful first-pass execution.

## Topics

AI Agents, Context Engineering, Software Development Lifecycle (SDLC), Computational Linguistics, LLM Architecture, AI DevCon NYC 2026, Anthropic, OpenAI, Thoughtworks

Source: https://www.youtube.com/watch?v=wBBCJinOes4