Beyond code generation: A developer's guide to agentic engineering
Beyond code generation: A developer's guide to agentic engineering
Nick Liffen & Philip Holleran · November 6, 2026 · GitHub Blog
This October, GitHub saw more than 1.2 billion commits in one week—over 400% more than a year earlier. A Faros AI study found that pull requests spent 441% longer in review when teams went from low to high AI adoption.
Agents can help across Plan, Build, Verify, and Observe:
Plan: Use Copilot in Slack/Teams to gather context; create Issues with acceptance criteria; use Agentic Workflows for triage; use Plan Mode before implementation.
Build: Session continuity across devices; cloud sandboxes; isolated repo copies per session; repository instructions and shared memory; Copilot Dreaming reviews sessions and PR feedback to keep memories current; Copilot Fusion to match models to the work; enterprise managed settings.
Verify: Stacked PRs; GitHub Code Quality; Copilot code review with depth matched to change size; AI Scan and AI secret detection; license compliance; Agentic Autofix and Agent Merge.
Observe: Connectors to observability tools; draft issues with evidence; review Dreaming suggestions for memories, skills, and review guidance.
Start with one frustrating part of your process and put an agent on it. Covered live at GitHub Universe 2026 in "Agentic Engineering: Past the Pilot."
https://github.blog/ai-and-ml/github-copilot/beyond-code-generation-a-developers-guide-to-agentic-engineeringReposted. Will be removed on request. All rights belong to the original author.
More from this batch
OpenAI reportedly raises an additional $11 billion at a $1.25 trillion valuation
Bloomberg sources say OpenAI has wired about $11B so far in a round valuing it at $1.25T, potentially totaling ~$20B—well below a prior ~$30…
中国国安据报策反 AI 高管 Alice Huang,目标刺探黄仁勋与先进芯片情报
The Verge 转纽约时报:MSS 据称招募 Megaspeed 高管 Alice Huang(与黄仁勋无亲属关系)搜集美国 AI 芯片情报,并可能推动先进芯片对华供应。上周已有「刺探黄仁勋」报道,本次新增「已被招募」细节;众议院三委员会要求黄仁勋闭门说明互动。属国家安全舆情…
The components of agent memory
Anthropic Engineering explains dreaming: offline passes that correct memory against transcripts, build wiki representations, and promote not…
New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration
Anthropic launches dreaming as a research preview on Managed Agents, plus outcomes rubrics and multiagent orchestration in public beta.
Claude Code 被指把用户邮箱塞进 User-Agent;v2.1.317+ 隐私插件默认拦截(issue 仍开放)
简报汇总 GitHub issue #107757:编码 Agent 向第三方站点发请求时 User-Agent 含邮箱;评论称多段 subagent curl 可复现。贡献者称 cc-plugin-privacy 自 2.1.317 默认开启。对企业:查版本与 /plugins…
Agent Plugins 1.0:Amazon、Cursor、Microsoft、OpenAI、Vercel 共同推进的可移植 Agent 扩展标准
开放标准:用 plugin.json + skills/ + mcp.json 打包 Skills 与 MCP,一次构建跨 Codex/Cursor/Copilot/VS Code 等加载。谱系明显借鉴 Claude Code 插件布局;Anthropic 未列联合维护方。对企业…
Perplexity now has its own always-on AI agent
Perplexity Teammates are always-on agents on dedicated VMs for ongoing projects, priced on the $200/mo Max plan.
AI Gateway adds DeepSeek Search and Fetch tools
Vercel AI Gateway exposes DeepSeek Search and Fetch as model-agnostic tools billed at $0.75 per 1k successful calls each.
Chat SDK agents can now stream generative UI with json-render
Chat SDK agents stream typed JSON UI specs via json-render into Slack/Teams native cards.
Speed Up Image Generation with FLUX 3 Image Klein on NVIDIA Blackwell GPUs
NVIDIA shows TensorRT LLM VisualGen optimizations that speed FLUX 3 Image Klein up to ~3.46× T2I / 4.45× I2I vs uncompiled BF16 on B200.
Ripple-65B Preview delivers strong agentic coding results as a fully Apache 2.0 open US model
Ricursive Intelligence open-weights Ripple-65B Preview (dense 65B, Apache 2.0) reports leading open-US TerminalBench scores at ~$32M total c…
TAC-CoT:工具增强的隐式 CoT——隐式段穿插显式工具调用,准度最高 +8.8、前向最高约 6.8× 更省
改进什么:显式 CoT 贵且易累积错误;纯隐式 CoT 难插工具调用。怎么做:用紧凑连续 thought token 做推理段,只在工具调用/观测/答案处保留文本,并按查询自适应段数。数学与 QA Agent 基准上相对 Explicit-CoT 提准并大减 #Fwd。KAIST…