Angie Jones (@techgirl1908) header
Angie Jones (@techgirl1908) profile picture

VP, Agentic AI Foundation. Helping developers build with agents. I ❤️ open source

New Orleans, LA
Joined December 2014
Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)Photo by Angie Jones (@techgirl1908)
The CFP for AGNTCon + MCPCon is open! 🎉 Come share what you're learning building with agents. Submit by January 18. events.linuxfoundation.org/a…
2
6
30
2,338
Angie Jones retweeted
What does software engineering look like when generating the code becomes cheap and verifying it is the hard part? A rare podcast focused on everything around building software, with @satyanadella. Timestamps: 00:00 Intro 02:12 Microsoft’s open-source shift 04:15 Building VS Code in the open 05:55 Copilot, Cursor, and Claude Code 09:52 Decision engines 12:32 Verifying AI-generated code 15:39 The software factory 20:45 Bringing AI to existing products 24:06 Why adopting AI is different to adopting React 26:29 The changing role of software engineers 29:25 Microsoft’s voluntary exit offers 34:05 AI anxiety and changing roles 36:35 Junior hiring 42:36 Open models 45:39 Owning your AI infrastructure 51:21 Building trust in AI agents 53:48 Local models and hybrid intelligence 56:39 Microsoft’s model strategy 59:26 Advice for engineers 1:01:21 Closing takeaways Brought to you by: • @turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. turbopuffer.com/pragmatic (I built a greatly improved podcast/newseltter search with it, check it out: pragmaticengineer.com/search) • @linear – the product development system for teams and agents. linear.app/pragmatic • @WorkOS – everything you need to make your app enterprise-ready. workos.com/ 3 interesting takeaways from Satya: 1. A new form of software engineering: teams building software factories to improve their work. Satya cites the Azure networking team which manages 500+ fiber network operators and recently built an agentic system to better manage emails and processes. Now, they operate much more efficiently as a result. Satya sees this as the reality of “AI transformation”: brownfield work on building software factories to improve how teams operate, all while continuing the day-to-day work. 2. “Own the intelligence”: avoid lock-in & treat agents as an insider risk. Satya cautions companies to avoid lock-in with any single model provider by ensuring that the harness, memory, and model are not coupled, so that they can be changed with ease. He also thinks more companies should consider using open models as a way to protect their core intellectual property (IP) from leaking out, and build private evals to decide what models to use and upgrade to. He also says that models are intelligent but unreliable, so it’s best to treat them as “insider risks” and build a separate system to verify that agentic systems work as expected. 3. What’s with those voluntary exit offers? I asked Satya directly why Microsoft recently made voluntary exit offers to most of its software engineers for the first time in the company’s history. I also wanted to know if it could mean layoffs in the future. Unsurprisingly, his reply was diplomatic, but in the podcast I rehashed what I heard in a more direct way.
115
71
12
513
38,739
Spoken aloud by a flight attendant: “Come on in folks, come on in before they lose a floppy disk or some shit” No notes 😂
35
1,058
26
17,077
217,623
Angie Jones retweeted
quick fixes considered harmful: you might be making your agents write worse code when you ask for the smallest or quickest possible change what seems like a harmless bandaid may lead to that pattern being copied by the next agent. before you know it that pattern has spread everywhere we used to write bandaid fixes by hand because we rarely had the time to do the right thing. agents change this calculus. sometimes you want it to fix the root cause instead even if it’s more invasive
349
261
148
5,242
328,677
Angie Jones retweeted
由 OpenAI 董事会主席兼前 Salesforce 联席 CEO Bret Taylor,联手前 Google Labs 掌门人 Clay Bavor 创立的百亿美金智能体独角兽 Sierra,刚刚正式发布 Personal Agent Protocol v1.0,简称 Poppy。 只用了一个月,Meta、Shopify、Stripe、Salesforce,甚至大家熟悉的 Manus、Browserbase 等 100 多家巨头和明星创企全部入局。 下面总结 5 条关键内容和案例: 1、以前个人智能体帮人办事,只能模拟人类去截图,看网页,点鼠标,又慢又容易崩。Poppy v1.0 相当于给所有网站立了一个智能体专用前台,直接把 MCP、OpenAPI 和 UCP 串成统一标准,让智能体一进门就能读取结构化能力清单,同时底层采用 OAuth 鉴权,用户随时可控权限,遇到付钱、转账等高危操作强制触发人类审批。 2、协议最怕没人用,但 Poppy 一上来就打通了供需两端。在流量侧,Meta 的个人智能体 Muse 已默认全量开启,访问任何网站第一件事就是自动寻找 Poppy 文件。在供给侧,覆盖 175 个国家的 Shopify 已为平台上所有商家自动生成并发布 Poppy 文件,全球数百万独立站无需写一行代码,直接具备接待个人智能体的能力。 3、Shopify 与 Sierra 联合编写了商务扩展,把智能体购物的全链路彻底打通,Poppy 负责进门握手(声明智能体身份、选游客模式还是登录账号、敏感操作前向用户讨要授权),UCP(通用商务协议)负责交易执行(搜商品、加购、结账),遇到复杂导购问题,还能通过 UCP Ask 让你的个人智能体,直接和店铺的客服智能体(A2A)对话。 4、不止电商,高风控行业已经实装上线,在硅谷金融平台 Mercury,个人智能体能直接查余额、给支出分类,甚至发起转账(底层强制走账户预设的审批流才会打款)。在土耳其航空,智能体能查票、用预订号调行程,还能帮会员盯商务舱里程升舱名额并推给用户一键确认,消费金融巨头 Synchrony 则支持智能体在跨 50 万家门店导购时,直接匹配免息分期和返现优惠。 5、最新加入的 100+ 合作伙伴名单中,除了传统金融和航司,还有 Salesforce(含 Agentforce)、Cisco、Zoom、Twilio,以及 AI 圈大家都熟悉的 Manus、Browserbase、WorkOS。 当日常任务全面交由个人智能体代劳,未来不能被智能体通过标准协议丝滑调用的网站,就像移动互联网时代没做手机端适配一样,会在无声无息中丢掉所有自然流量。
Today we’re releasing Personal Agent Protocol (Poppy) v1.0. It’s on for everyone who uses Muse, @Meta's AI agent, enabled for every merchant on @Shopify, and backed by more than 100 design partners.
18
96
10
1,272
166,295
Angie Jones retweeted
I added WebMCP to my site. Now an agent asks my site what I've published on MCP and gets the answer in one tool call, about 562 tokens. Reading the four MCP tag pages as HTML instead: about 99,000 tokens. Here's how it works in Chrome DevTools 👇
37
21
3
416
34,357
Angie Jones retweeted
I just finished talks about my software factories at two conferences. Afterwards a bunch of people came up and told me what they were surprised about. Here is a distillation of what people thought were hot takes from my two talks. First hot take: I tell everyone to slow down. Most speakers go on about how fast they're going, but I strongly believe in pacing AI outputs to human speeds. I regularly tell AI-pilled CIOs and CTOs to chill: almost nobody is _actually_ going fast with AI. Engineering still moves at engineering speeds, and business moves even slower. The ones pushing too hard are starting to see downtime for it. If you don't pace your AI to human speeds, everything starts breaking around you, even at small operations like my online video game. I only have about a dozen humans working with my factory, and only a few hundred active old-timer players in the community who get along well, and still, introducing AI has still been very rocky. My agents have, at times, overwhelmed my players with features, my accountant with emails, my merge queue with tickets, and my machines with load. Agents have pissed off my admins, resulting in name-calling, they've made messes in the game, and they've launched broken OSS without permission. The list goes on. I can get away with all this chaos because everyone involved in my operation is very forgiving. They're excited by the potential. But even so, I had to learn to slow down, real fast. And so that's what I preach. Hot take #2: Should you buy a software factory? Do you even need one? No. You probably don't need one. Factories take an extraordinary amount of upkeep. They turn into garbage mountains unless you put a frightening amount of time and tokens into curating them. I had to burn my previous five factories down since it eventually became cheaper to rewrite them than to fix them. So I'm not out there advocating for software factories or swarms just yet. If you do want one, be aware that it is a significant commitment of both money and human leadership to keep one running. Several people told me that I was the only one who stood up onstage, at either conference, and said Build, don't Buy. But my experience is that software factories grow to be highly bespoke to your domain. Mine is super tangled up with my game, and I think that's inevitable. Because the factory is not just building my product, it's supporting it too. It's a company in a box. And they're easy for Claude to build for you. Third and arguably hottest take: Next year will have a lot of human/agent and agent/agent office drama, resulting from bringing in AI employees, and it will be gloriously funny, but also frustrating. Many of you are already on this bandwagon, but everyone next year will have a personal chief-of-staff agent. Busy people, even hobbyists, will have whole entourages of helper agents. The hot take is that people will become so dependent on these little private entourages, that they'll bring them to work. Your people will talk to my people, etc. Whole protocols will emerge for private entourages negotiating work between humans, inside companies big and small. Nearly all humans will wind up having to start working with AI employees next year, and it'll be the beginning of the biggest cultural change we've seen in a hundred years. So that's the hot takes. Slow down. Only build a factory if you think you really need one. And focus on empowering yourself with your own agentic chief of staff (or team). Your entourage will define how you work with others, so start by perfecting how you work with them yourself.
188
303
102
2,826
319,896
really comical how the default demo for AI agents is booking travel and yet i can't even get my agent to check me into my flight without me staying in the loop to approve captchas, OTPs, etc 🗣 I do not want to be involved!
12
1
56
4,517
Angie Jones retweeted
Personal agent protocol is officially launched! 🚀 Very proud for Ora to be an early partner. It's challenging to standardize a spec across the industry (I know), but it's critical for pushing the entire web forward. We're building the true Agentic Web. 👏 @SierraPlatform
Today we’re releasing Personal Agent Protocol (Poppy) v1.0. It’s on for everyone who uses Muse, @Meta's AI agent, enabled for every merchant on @Shopify, and backed by more than 100 design partners.
5
6
1
68
5,656
Angie Jones retweeted
I am an elder millennial. I promise you that if I am calling, I already know I cannot solve this issue online. PLEASE LET ME SPEAK TO A PERSON.
102
3,001
129
29,157
376,217
Stripe cut 500,000 internal docs down to 5,000. @capitaltruist of @falconer_ai explains why stale documentation, conflicting context, and unclear ownership can lead AI agents to make costly engineering mistakes.
6
4
1
15
1,486
Angie Jones retweeted
Want to know if your GitHub repositories or any of the open-source projects you depend on were targeted by the WFX Phantom attack? We built a tool to help you check: github-pulse.eon.io/attack-t…
In the last two days, 4,837 hijacked GitHub accounts opened pull requests in more than 61,000 repositories. In at least 1,835 of them a script ran inside CI, stole the secrets and covered its tracks, sometimes within seven seconds. Last week, we launched Eon Yukon, our new data engine for the AI era, and built GitHub Pulse to demonstrate its ability to process massive streams of GitHub activity in real time. When the attack started, we realized we already had the data to track it. So we built a live attack tracker. Check whether your repos or the open-source projects you depend on were targeted: github-pulse.eon.io/attack-t…
1
3
565
4,200+ builders. 1,000+ organizations. 11 tracks. Two days of pushing agentic AI forward. AGNTCon + MCPCon North America 2026 brought the community together in San Jose to tackle interoperability, security, and what it takes to build production-ready AI agents. Relive the highlights from our largest AAIF event yet. Next up: San Francisco, April 28–29: bit.ly/4kpYmYz
2
8
854
How to turn slop into gold. Super concrete steps from awesome @poteto on making coding agents trustworthy: 1. Clean up the code your agents learn from. Your codebase is one of their biggest inputs. Agents copy whatever looks like an established pattern, including workarounds, deprecated code, and yesterday’s questionable decisions. Clean those up, or watch them reproduce. 2. Turn corrections into enforceable checks. Every time you correct an agent, ask: can this become a lint rule, a type constraint, a test, or a better API? Put the correction somewhere the system can enforce it. A growing AGENTS.md still requires the agent to follow every instruction. 3. Remove opportunities for predictable mistakes. Her team @SpaceXSI restricts React’s useEffect to framework internals because agents repeatedly misuse it in product code. They also enforce import boundaries between application processes. These constraints eliminate whole categories of mistakes that would otherwise keep coming back in review. 4. Give agents a reliable way to run and inspect the product. Provide debugging tools, reusable CLIs, and a “feature map” describing the application from the user’s perspective. Now “that thing in the left sidebar” has a shared meaning, and each agent can reuse the tools for checking it. 5. Review evidence of behavior. Have agents produce screenshots, videos, and state diagrams. These help you check what the product actually does and how closely that matches your intent. A convincing explanation of a fix is easy to generate; seeing the fix work is considerably more useful. 6. Spend serious effort on verification. Her team uses runtime verification and is experimenting with property-based UI testing and formal methods, including TLA+ model checking. Lauren says most of her token usage goes toward verification. Agents make some previously expensive testing work much more practical. 7. Automate once that loop is reliable. Her team now has agents exercise new releases, find bugs, open fixes, and merge them automatically. Getting to that level of trust took her about six months of investing in the environment. The results she reports: 11,000 pull requests shipped by her team in a month, a revert rate around 0.5%, and improvements in startup, typing, and switching chats. And what about infamous “software factory”? if your coding loop produces slop, automating it produces more slop, faster, with a larger token bill. Start by making good code the easiest thing for an agent to produce. Then scale it. As always, content at @aiDotEngineer is gold 🏆
49
165
15
2,401
164,044
Today we are releasing A2UI 1.0, now faster, easier, and stable, an open protocol and framework for generative UI across web, Android, iOS, wearables, TVs, and any other surface. 👇 Check out what shipped
69
107
44
739
64,673
What happens when AI agents can actually learn from experience? @yaboilyrical of @NousResearch breaks down how Hermes Agent builds reusable skills, retains context, and improves over time instead of starting from scratch with every session.
4
5
2
31
5,332
Angie Jones retweeted
VS Code Insiders now supports skills-over-MCP! Enable it in your settings, then try a server that has skills, or whip up a @fastmcp server with some skills. Run into issues? File them in microsoft/vscode repo - already got one fixed today!
3
5
28
2,158
A short AGENTS.md file made a measurable difference in a coding agent's work on the TODO Group website. Across 18 runs: 36% fewer tokens, 32% less time, and 26% lower estimated costs. AAIF Ambassador @anajsana95 shares the experiment, method, and limitations. aaif.io/blog/devex-for-your-…
4
1
8
1,298
Agentic engineering, enterprise adoption, evals and reliability, security, agent interfaces, and agentic AI 101. Pick your track and submit to speak at AGNTCon + MCPCon North America 2027, April 28-29 in San Francisco. Deadline: January 18. Submit here >> bit.ly/4tFfCdz
1
2
3
727