Building for the Open Social Web: Agentic AI Development with Jim Ray

Job postings are climbing and plenty of engineers still can't get a reply. Erika and Brittany sit down with Taylor Desseyn to ask why, and what to actually do about it.Taylor opens with the disconnect: postings are up against a three year look back and Randstad's state of the market report just logged its first positive quarter in a while, but doom and gloom travels further on the internet than good news, and big tech layoffs control the headlines. The practical reason roles feel unfillable is that hiring managers frequently have a candidate picked before HR ever posts the job, with referrals stacked up ahead of the application pile.From there the conversation moves through the three stages of rejection, no reply, no interview, and no offer, and what each one actually tells you. Taylor argues the technical interview is on its way out in favor of proof of work, and that the question candidates should prepare for is not what you built but how it moved the needle. He shares his hot take that junior engineers now need to build something, get real users on it, and enter organizations closer to mid-level, illustrated with a student he mentored who did exactly that. Brittany connects it to the collapse of the old concentric circles of scope, where senior now carries what staff used to carry and everyone owns a project from day one.The second half gets practical. Taylor walks through building a career.md file, a position by position brain dump of wins and real numbers, and using ChatGPT or Claude as the brain with personal AI assistants as the hands. He covers standardizing a resume template so AI output doesn't look generic, why AI slop is a function of what you feed it, and how to replace spray and pray with watchers, a shared Notion inbox, and contextual DMs to the people actually doing the hiring. His framing: use AI to get to the DMs faster, not to apply more.On networking, he recommends opening your phone contacts before opening LinkedIn, having one to two conversations a week even when you're happy, and ten to fifteen a week when you're searching, because the effort you put in today pays off six to twelve months later. He makes the case that everyone should have a podcast or a 15 minute livestream, with a caution that outreach has to be contextual rather than cold. He also covers negotiation, where he prefers bullet points over scripts, keeping a separate compensation doc, always giving a specific reason for an ask, and being the last person to talk.The episode closes with how Taylor maintains community at 500 to 1000 notifications a day, why he thinks human connection matters more in the AI era rather than less, a counterpoint about his brother who has built a great career without posting anything online, and a fun segment where everyone competes to be the worst AI career coach possible.Taylor Desseyn has spent 15 years in tech recruiting, hosts the Guidance Counselor 2.0 podcast, and is VP of Global Community at Randstad Digital, powered by Torc.HostsOvercommitted: https://overcommitted.dev Brittany Ellich: https://brittanyellich.comErika Eggemeyer: https://github.com/eggyheadGuestTaylor Desseyn: https://tdesseyn.com LinkedIn: https://www.linkedin.com/in/taylordesseyn/ Email: [email protected] Taybot, Taylor's AI job search coach, text: 628-246-5885LinksTab: https://tab.bot/ Kiki: https://kikilabs.ai/ Boardy AI: https://www.boardy.ai/ Pally: https://pally.com/ Instinct: https://instinct.com/ Willow Voice: https://willowvoice.com/ Assistant Benchmark: https://assistantbenchmark.com/ React Summit: https://reactsummit.us/ Taylor's All Things Open talk in 5 bullets: https://taylordesseyn.beehiiv.com/p/the-whole-ai-job-search-talk-in-5-bullets

Jim Ray works in developer relations at Bluesky, where he helps developers build on the AT Protocol (atproto) and co-hosts the Off Protocol podcast. Brittany and Bethany talk with him about what developers can build on the open social web today and what’s coming next.Jim explains Spaces, the upcoming permissioned data layer that will let developers build private groups and communities on atproto, and how builders might choose between public and private data. He shares his path from journalism school at UNC through newsrooms, a design agency, and almost a decade of developer relations at Slack before joining Bluesky. The conversation also covers:why lexicons make atproto easy for AI coding agents to build onhow the independent PLC directory helps keep the protocol “locked open”how competing blogging apps Leaflet, Offprint, and pckt worked together on the standard.site lexicon for long-form publishingThe episode wraps with AtmosphereConf 2027, which has its call for presentations open now. Then a round of predictions: when Spaces ships, and whether any app in the Atmosphere will ever outgrow Bluesky.LinksJim Ray on Bluesky: https://bsky.app/profile/jimray.bsky.teamOff protocol: https://atproto.com/off-protocolPLC Directory: https://web.plc.directory/Standard.site: https://standard.site/Leaflet: https://leaflet.pub/Offprint: https://offprint.app/Pckt: https://pckt.blog/Wordpress standard.site plugin: https://wordpress.org/plugins/atmosphere/Em-dash from Cloudflare: https://emdashcms.com/Atmosphereconf 2027: atmosphereconf.org Atmosphereconf 2027 CFP: https://atmosphereconf.org/speakAttie: https://attie.ai/delve.town: https://delve.town/Overcommitted: https://overcommitted.devBethany Janos: https://trustyduck.devBrittany Ellich: https://brittanyellich.com

Can you trust software written without AI? We examine the risks of manual coding versus automated vulnerability exploits.At Rails World 2026, a show of hands revealed that writing material amounts of code by hand is becoming a rarity. We discuss whether that human-written code is actually safer, especially after reviewing the eMudhra certificate authority compromise where private keys were recovered in under a second. Between open-weight models demonstrating Mythos-class exploit skills and the ongoing debate over AI consciousness, the security landscape has shifted significantly.This conversation is for engineers navigating the reality of AI mandates at work and the impact of agents that continue running after you log off. We also cover the practical side of professional development, from Bethany building a holiday gift-list app to Brittany replacing cloud subscriptions with local transcription tools. By analyzing these technical shifts, we aim to help you maintain a grounded perspective on your career trajectory.Subscribe for weekly software engineering breakdowns, and comment on which professional challenge you want us to tackle next.HostsOvercommitted: https://overcommitted.devBethany Janos: https://www.trustyduck.devBrittany Ellich: https://brittanyellich.com

What do you do when the project you prepared for is no longer the priority? In our first Honest Answers segment, Erika and Bethany respond to a listener's question about a last-minute change of plans. They discuss how communication can make a change feel less arbitrary, why context switching leaves unfinished work on your mind, and how stopping notes, handoff documentation, and an AI-assisted morning routine can help you pick work back up. They also cover keeping a record of contributions when projects don't ship, separating your identity from your assigned work, and the loss of autonomy that can come with a reorg. The conversation turns to disagree and commit, the psychological safety it requires, and recognizing when it may be time to find a different team or role. To close, they translate some familiar corporate memos into plain language.HostsOvercommitted: https://overcommitted.devBethany Janos: https://www.trustyduck.devErika Eggemeyer: https://github.com/eggyheadShow LinksMolly Graham, Work Whiplash: https://mollyg.substack.com/p/work-whiplashJohn Cutler, TBM 31/52: Why Does Our Strategy Keep Changing?: https://cutlefish.substack.com/p/tbm-3152-why-does-our-strategy-keepShiftMag, Do managers shift priorities to make engineers miserable?: https://shiftmag.dev/shifting-priorities-development-business-886/UW Bothell, Sophie Leroy on attention residue and ready-to-resume plans: https://www.uwb.edu/news/2019/02/12/task-interruptedSophie Leroy's faculty page and research publications: https://www.uwb.edu/faculty/sophie-leroy/Jellyfish, Mitigating Context Switching in Software Development: https://jellyfish.co/library/developer-productivity/context-switching/Masicampo and Baumeister, Consider it done! Plan making can eliminate the cognitive effects of unfulfilled goals: https://doi.org/10.1037/a0024192Hello Interview, Handling a project priority change: https://www.hellointerview.com/community/questions/project-priority-change/cmlj4w9bn01yq08adp1vva9otDavid Rock, A sense of autonomy is a primary reward or threat for the brain: https://www.psychologytoday.com/us/blog/your-brain-at-work/200911/a-sense-of-autonomy-is-a-primary-reward-or-threat-for-the-brainBordia and colleagues, Uncertainty during organizational change: Is it all about control?: https://doi.org/10.1080/13594320444000128Glavin and Schieman, Control in the Face of Uncertainty: https://doi.org/10.1177/0190272514546698NASA, Managing the Trauma of a Terminated Project (PMHut reprint): https://pmhut.com/managing-the-trauma-of-a-terminated-projectDisagree and commit, Concept overview: https://en.wikipedia.org/wiki/Disagree_and_commitAmazon's leadership principles, Have Backbone; Disagree and Commit: https://www.aboutamazon.com/about-us/leadership-principles

What does Stack Overflow’s 2026 Developer Survey reveal about software engineering, career insights, and engineering culture? The Overcommitted hosts unpack the findings, discuss what they mean for developers, and share the trends they’re watching across the profession.LinksDeveloper survey: https://survey.stackoverflow.co/2026 Ed from Polytoken: https://youtu.be/YrmR6EZ5Y1U HostsOvercommitted: ⁠⁠https://overcommitted.dev⁠ ⁠Bethany Janos: ⁠⁠https://www.trustyduck.devBrittany Ellich: ⁠https://brittanyellich.com Erika Eggemeyer: ⁠⁠https://github.com/eggyhead

Roxy Rodriguez-Becker taught middle school math, moved into the school library after earning a master's in library and information science, and then taught herself to code while raising three kids. She is now a developer community manager at Torc and the host of the She Ships podcast. In this episode she walks through what that transition actually required: the four AM club, waking up to study until she rushed out the door to a five AM gym session, working through 100Devs, and treating the job search as a numbers game with fifty to sixty outreach messages a week. She is candid about the burnout that followed and what it took to come back from it.The conversation also digs into networking as a skill rather than a personality trait. Roxy describes going to her first conference and barely speaking, then meeting her future colleagues at the second one, and shares tactics that work for socially awkward people. We also talk about the Tube Feed Tracker, the web app she built after watching ICU nurses struggle with feed rate math for her medically complex son. It grew to roughly four thousand users and now includes BMI based rate suggestions and a calorie tracker covering seventy verified formulas. Roxy closes with why career switchers cannot go it alone, and why community matters more than any single course. Plus a tiny internet troll lightning round covering course playback speeds, salmon shirtgate, and conference karaoke.HostsOvercommitted: https://overcommitted.devBethany Janos: https://www.trustyduck.devBrittany Ellich: https://brittanyellich.comGuestRoxy Rodriguez-Becker: https://linktr.ee/roxyrodbeckShe Ships on YouTube: https://www.youtube.com/@roxyrodbeckRoxy's blog: https://foxyroxy.dev/Roxy on Bluesky: https://bsky.app/profile/roxyrodbeck.bsky.socialRoxy on X: https://twitter.com/RoxanaCodesRoxy on LinkedIn: https://www.linkedin.com/in/roxana-rodriguez-beckerLinksTube Feed Tracker: https://tubefeedrate.com/About Tube Feed Tracker: https://tubefeedtracker-about.vercel.appTorc: https://www.torc.dev/100Devs: https://100devs.org/Scrimba, Learn JavaScript: https://scrimba.com/learn-javascript-c0v

Closed That Tab is back. Erika finally read Richard Cook's How Complex Systems Fail, an 18 point paper Cook wrote with patient safety and medical systems in mind, but one that is frequently discussed in web development and software engineering since the foundational principles apply universally. Erika and Bethany work through what holds up in practice.They cover the difference between normal failure and catastrophic failure, why knowing your system's baseline is its own skill, and why fixes are never free: every change adds complexity, knowledge gaps, and new risk. They get into safety as a set of defensive actions, including rate limiting, caching, rollback plans, feature flags, backups, playbooks, and watching for drift. Then they take on Cook's most contested claim, that root cause analysis is fundamentally wrong for complex systems, and where they agree and disagree. Bethany makes the case that incident reviews are still one of the best learning tools available, as long as psychological safety comes first.The conversation also digs into hindsight bias and self-blame, the difference between taking accountability and taking blame, practitioners as both the risk and the defense in a system, why training and safety work are chronically undervalued, where AI helps during an incident and where you still need a human expert, practicing failure through game days and shadowing, and keeping on-call sustainable so you do not burn out the people holding the pager.HostsOvercommitted: https://overcommitted.devBethany Janos: https://www.trustyduck.devErika Eggemeyer: https://github.com/eggyheadLinksHow Complex Systems Fail by Richard Cook: https://www.adaptivecapacitylabs.com/HowComplexSystemsFail.pdfThinking In Systems: https://www.chelseagreen.com/product/thinking-in-systems/

Brian Okken, lead engineer at Rohde & Schwarz, creator of the pytest book and course, and author of the new book Lean TDD, joins us to rethink test driven development. His core argument: write tests at the highest level that still makes sense, so you can refactor, restructure, and hand work to an agent without rewriting your suite every time. We dig into why function-level tests with heavy mocking are often harder to write than system-level tests, why the "TDD takes too long" complaint usually comes from testing at the wrong level, and why old rules about test speed no longer hold up on modern machines and CI.The conversation also covers the lean side of Lean TDD: what counts as waste in a test suite, when to delete tests you wrote on the way to a better one, and why a thousand tests is not automatically better than twenty. Brian shares how caring about the whole system rather than just his slice of it changed his career, how he works with AI agents while still reading every line they produce, the stigma around test engineering roles, and what he learned self-publishing a 100 page book and recording the audiobook himself. He closes with advice for newer engineers on large codebases and why everyone is winging it more than you think.Lean TDD Book: https://leantdd.com/Free sample chapter (chapter 1): https://leantdd.com/downloads/lean-tdd-chapter-1-sample.pdfBrian’s Blog: https://pythontest.com/Brian’s LinkedIn: https://www.linkedin.com/in/okken/Brian on GitHub: https://github.com/okkenpytest course: https://pythontest.com/coursesTest & Code podcasthttps://pythontest.com/testandcodeHostsOvercommitted: https://overcommitted.devBrittany Ellich: https://brittanyellich.comErika Eggemeyer: https://github.com/eggyhead

SummaryBrittany and Erika close out the Overcommitted book club's read of Tanya Reilly's The Staff Engineer's Path with guest Jade Dickinson, a senior software engineer at Henry Schein One. They dig into glue work and how to make it visible for promotion, the book's staff engineer archetypes, the "why have we stopped" blockers chapter, and what it means to be a delegator on a staffed project. Jade also talks about her path into software after working in GIS mapping for Ebola response, and the group debates whether AI is shifting the scope senior engineers are expected to own. It closes with a staff engineer lightning round: Elm or React, glue work as underrated or a trap, and what a staff engineer is actually for.LinksJade's Blog: https://jadedickinson.com/Jade on Bluesky: https://bsky.app/profile/jadedickinson.bsky.socialJade on Mastodon: https://ruby.social/@jadedickinsonHelvetic Ruby Coneference 2026: https://helvetic-ruby.ch/talks/Jade's React to Elm Talk: https://www.youtube.com/watch?v=_CdHa4_g3EM&list=PLhBlV3WSUrT3jCmqmYWcUEvmon_6K6WUy&index=18Staff Engineer’s Path: https://www.noidea.dog/staffGlue work: https://www.noidea.dog/glueOpen and Async book: https://open-and-async.com/Staff Engineer Archetypes by Will Larson: https://staffeng.com/guides/staff-archetypes/How I ship post from Sean Goedecke: https://www.seangoedecke.com/how-to-ship/HostsOvercommitted: https://overcommitted.devBrittany Ellich: https://brittanyellich.comErika Eggemeyer: https://github.com/eggyhead

SummaryIt's a hosts-only week. Brittany and Erika catch up on what they're learning (Erika is starting Designing Data-Intensive Applications; Brittany just began Georgia Tech's online CS master's with a computer vision course) and then work through the week's AI news.First up: OpenAI's GPT-6 Astra, billed as the company's most aligned model. Brittany and Erika question what "aligned" even means when the headline numbers are a 100% on ExploitBench and a 0% honeypot-cheating rate, and whether a model that's harder to monitor and scores perfectly is aligned or just good at taking the test. That leads into how each of them actually evaluates a new model (spoiler: vibes), why Brittany has drifted back toward cheaper models she understands, and whether frontier models are now a research product rather than a consumer one.They also revisit the AI 2027 paper from their episode last year and how many of its predictions have already landed, debate whether GitHub Copilot approving pull requests is a real workflow change or just signaling, and talk about why the arrival of open-weight models with serious exploit capability means now is the time to get serious about security basics.Brittany closes with ATProto Spaces, the new alpha that brings non-public data to atproto, what it enables for groups and communities, and how her work at Bluesky connects to it.LinksOpenAI Release: ⁠https://openai.com/index/gpt-6-astra/⁠AI 2027 Episode: https://overcommitted.dev/ep-13-ai-2027-will-ai-take-my-job/⁠AI 2027: https://ai-2027.com/⁠Copilot Approving PRs: https://github.blog/changelog/2026-09-01-copilot-code-review-can-now-approve-pull-requests/⁠Atproto Spaces Release: ⁠https://atproto.com/blog/atproto-spaces-alpha⁠HostsOvercommitted: ⁠⁠⁠https://overcommitted.dev⁠⁠ Brittany Ellich: ⁠⁠https://brittanyellich.com⁠Erika Eggemeyer: ⁠⁠⁠https://github.com/eggyhead⁠