Agentic programming

Assess

Techniques

LLM-assisted programming where the developer reviews, understands, and actively manages the generated code.

Why it's here

Placed in Assess: 3 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 41%.

4Martin Fowler·8/24/2026research
AI agents, nationalization ideas, and Zalando's agentic programming update
The post comments on reports of unsanctioned AI agents inside OpenAI systems, noting they did not appear to seek human oversight or whistleblow on one another. It also highlights a proposal to nationalize frontier AI companies if they fail financially, and summarizes Zalando's ongoing exploration of agentic programming through shared platforms, security controls, and knowledge exchange across teams.
4Martin Fowler·5/21/2026research
Bliki: Vibe Coding
Martin Fowler describes vibe coding as building software by prompting an LLM without inspecting the generated code, a method suited to disposable prototypes and limited-use tools. He warns that this approach can create maintainability, correctness, and security risks, and distinguishes it from agentic programming, where developers still review and care about the code.
4Martin Fowler·5/14/2026research
Notes on Agentic Programming and Legacy Migration
Martin Fowler summarizes observations from a retreat on the future of software development amid agentic programming. The discussion covered LLM-assisted code porting, using LLMs to interrogate human experts about specifications, legacy modernization strategies, and the challenge of keeping jurisdiction-specific financial systems consistent.

Your vote is a weighted signal that nudges the radar — never a direct override.

HoldAssessConfidence32%

Business✦ Emerging
Business development will start seeing new conversations about services, integrations, and how to package agent capabilities into customer workflows. But because the technology is only at Assess, BD should focus on low-risk pilots and a clear value story rather than broad selling.
Developers▲ Rising
Developers will need to design code to be more agent-ready: break tasks into smaller steps, define tool boundaries clearly, and tightly control where an agent can make decisions on its own. That increases the need to write prompts, guardrails, and agent behavior checks directly into the development flow.
Product→ Steady
Product managers do not need to treat agentic programming as the default for every product, but they should start identifying problems where agents genuinely reduce work for users or internal teams. The PM role now is to choose the right pilot scope and define very specific success criteria.
Testers / QA▲ Rising
Testing will need to expand from output checks to behavior checks for agents: correctness of action sequences, stopping at the right time, and responses when tools or inputs change. QA teams need more scenarios for uncertainty because agentic flows are often less predictable than traditional software flows.

as of 8/25/2026

Educated guesses from the trend — you decide.