Agentic coding
TrialTechniques
A coding workflow where an AI agent plans, executes, and iterates on programming tasks.
Why it's here
Placed in Trial: 11 article(s) of evidence from 6 source(s), led by research-stage coverage, with 3 in the last 30 days. Confidence 93%.
Evidence (11)
- 5Hacker News·10/2/2026researchThe Four Risks of Agentic Coding
The article argues that agentic coding systems face four major failure modes that limit their reliability in real software work. It frames these issues as practical obstacles for using AI agents as autonomous coding assistants rather than as general-purpose productivity boosters.
- 7InfoQ·10/2/2026framework_updateUber Eats Rebuilds Search Pipeline to Halve Latency
Uber rebuilt major parts of the Uber Eats search pipeline and says the changes cut end-to-end latency by 50%. The work included Above-the-Fold measurement, reduced retrieval, parallel hydration, advertising data redesign, infrastructure tuning, and an agentic coding workflow, with further exploration of microbatching, product-based retrieval, and HTTP multipart streaming.
- 7The New Stack·9/30/2026product_launchCloudBees shifts to an AI-first strategy
CloudBees CEO Mo Plassnig says the company is pivoting to an AI-first model as generative AI rapidly increases software output in enterprise environments. He argues that enterprise DevOps teams will need stronger process, governance, and security controls to manage the growing volume of machine-generated code.
- 7The New Stack·7/29/2026researchShipping Code Without Human Verification
The article argues that agentic coding is making traditional human code review a bottleneck, especially for verification tasks. It proposes shifting teams toward automated verification systems and a “human on the loop” model, where people maintain the review infrastructure instead of checking every change themselves.
- 4Martin Fowler·7/8/2026researchExperiences running local coding models
Birgitta Böckeler reports on testing small language models locally on developer machines for agentic coding, focusing on speed, tool use, context handling, and code quality. She compares manual and automated evaluations, then uses the most promising model in day-to-day work to judge practical viability.
- 4Martin Fowler·7/7/2026researchAssessing local coding models on modern Macs
This article discusses the practical viability of running local models for coding, including agentic coding, based on the author's recent hands-on experience. It focuses on factors such as model runtime, quantization, architecture, hardware, context size, and tooling that affect quality, speed, and tool-calling reliability.
- 4Hacker News·7/7/2026product_launchDeveloper checks Garry Tan’s claim of 37K lines of AI code a day
A Hacker News-linked Fast Company article reports on Y Combinator CEO Garry Tan’s claim that he ships about 37,000 lines of AI-generated code per day. A developer examined the underlying code and discussed how much of it is actually useful, highlighting questions about code quality, review, and the role of agentic coding tools. The discussion centers on whether large volumes of generated code translate into real productivity gains.
- 6Hacker News·6/29/2026model_releaseOrnith-1.0: Self-improving open-source models for coding agents
Ornith-1.0 is presented as an open-source model project focused on self-improvement for agentic coding tasks. The GitHub release is drawing Hacker News attention for its emphasis on models that can iteratively improve their coding performance in agent workflows.
- 3Simon Willison·6/28/2026researchJon Udell on Reframing Human-in-the-Loop Work
Jon Udell argues against the phrase “human in the loop,” saying it implies machines are in control. He proposes framing agent-assisted development as a human-led workflow where agents are invited into the team and processes remain reviewable rather than black-boxed.
- 5Martin Fowler·4/2/2026researchHarness engineering for coding agent users
The article proposes a harness engineering mental model for coding agents to improve trust in AI-generated code. It argues for combining feedforward guides and feedback sensors, using both deterministic tooling and semantic evaluation to reduce errors before human review.
- 7OpenAI Blog·3/19/2026researchOpenAI monitors internal coding agents for misalignment
OpenAI describes how it uses chain-of-thought monitoring to study misalignment in internal coding agents. The approach analyzes real-world agent behavior to identify risks and improve AI safety safeguards.