Rob Clevenger

I've just open-sourced gsearch-cli 🚀 If you're using the official Gemini CLI, you likely know the convenience of having AI-powered search in your terminal. But sometimes you just need a quick, grounded search without the full agent overhead. Introducing gsearch-cli: A standalone, blazing-fast Rust CLI for grounded Google Web Search powered by the Gemini API. The best part? It shares authentication credentials seamlessly with the official Gemini CLI (`~/.gemini/oauth_creds.json`). If you're already logged in, you're ready to search—no redundant logins required. 🚀 Key Features - Shared Authentication: Uses the same token storage as the official gemini-cli. - Grounded Results: Returns search results with citation markers and a clean list of source links. - Speed: Natively compiled Rust for instant results. - Focus: A dedicated, focused tool for research tasks. Take a look on GitHub, and if it improves your terminal workflow, drop us a star! 🌟 https://lnkd.in/gd2m8Ea6 📦 Install: - Homebrew: brew install aeroxy/gsearch-cli/gsearch - Cargo: cargo install gsearch-cli

1

If you're keen on real AI use cases, this is actually quite powerful and I encourage you to read further (and help us build: https://lnkd.in/gsYnAfKK) At Hex, we've found our Threads product (https://lnkd.in/gJKCurJB) is the best way to summarize customer support load, because we're not limited to what's in the customer support portal - we can ask in terms of active users, customer size, feature adoption, and still get great answers. This is based on a strategy of keeping your data warehouse as a source of truth, and all related data work in one place - Hex - so that AI understands concepts in your business and makes smart connections between things. Arguably, ALL data analysis for a particular vertical is eventually best achieved in a tool like Hex, connected to curated data in your data warehouse. Wait - can't I do this directly in the customer support tool? Can't I connect an MCP server and get a functionality like this in one of my other AI enabled products? Maybe, but you have 100+ SaaS apps, so play this scenario out: - How many places are you going to sync your core data sets? - How many cross product integrations are going to exist, and how many of them are you going to enable? (100 choose 2 is ~5000) - In how many of these products will all users have seats? - In how many of these products will these seats have permissions to use AI features? (Our support tool just told me I don't have permission to ask the agent questions, probably because I don't have the right seat type, which means more $$) My bet is a on a world with ONE place for all analysis.

33

2 Comments

New blog post: A Fork in the Road: Deciding Kafka's Diskless Future. Kafka is getting serious about S3 and finds itself at an architectural crossroads that will shape its next decade. Several new KIPs (1150, 1176, 1183) aim to reduce replication costs across cloud availability zones, but the implications go far beyond networking cost. It’s a mistake to think of S3 as simply a cheaper disk or a networking cheat. Building on object storage opens the door to operational benefits such as elastic, stateless compute — something many modern analytics systems already exploit. In my latest post, I outline two competing future paths: 🔹 Evolutionary path: Reuse large parts of existing Kafka components to reduce code changes and long-term maintenance. 🔹 Revolutionary path: Separate stateless and stateful layers to realize the full operational benefits of disaggregated storage. The post examines the trade-offs of each path, how the current KIPs map to these two paths and poses a broader question: what should Kafka become? And what will keep it relevant in the decade ahead? https://lnkd.in/d4E2BAe4

149

12 Comments

How Replit Agent 3 Pushes Engineers from “Coding” to “Supervising Systems” Replit’s Agent 3 is a real step toward autonomous software delivery - not just “AI-assisted coding.” Here’s what actually changed and why it matters. What it does (beyond code suggestions) * Self-testing in a real browser: Periodically spins up a browser, drives the UI (clicks, forms, auth), summarizes findings, and patches regressions in-loop. You can watch the cursor in the Agent pane as it validates buttons, forms, APIs, data sources, and Replit Auth flows. * Autonomy with guardrails: Replit reports 10× more autonomy than v2 and a testing system 3× faster and 10× more cost-effective than generic “computer use” models. Tests trigger when enough has changed - not after every message * Max Autonomy (beta): Runs for ~200 minutes with self-supervision and progress tracking - useful for multi-step refactors or feature builds that need uninterrupted execution * Builds other agents & automations: From Slack/Telegram bots to scheduled workflows (e.g., daily Linear/Notion summaries) via a guided credentials flow (Notion, Linear, Dropbox, SharePoint). Turns “glue work” into natural-language recipes the agent implements Why it matters for teams * Shorter feedback loops: A tight build → run → test → fix loop reduces context switching and catches UI/API integration issues earlier * Reduced integration overhead (credentials, SDKs, OAuth) frees engineers to focus on specs and review * Supervisory posture: Engineers shift to specifying intent, constraints, and acceptance criteria - less line-editing Operational considerations * Production safeguards: Keep backups/versioned deploys; gate production mutations until evaluations pass * Stop conditions & scope: Define time, scope, and blast-radius limits for Max Autonomy sessions. Require approvals for schema/migration steps; prefer data migrations behind feature flags * Traceability: Treat the agent like a junior dev with root - mandate PRs, CI, signed commits and human review on sensitive repos Bottom line Agent 3’s browser-level self-testing, multi-hour autonomy, and built-in automations make it a credible candidate for supervised autonomy across parts of the SDLC. Teams that write crisp specs and enforce guardrails can compress iteration cycles - while keeping humans accountable for outcomes. https://lnkd.in/gravaSWA #ai #artificialintelligence #aiagents #coding

8

TL;DR: Claude Code’s extensible agent system lets you create custom sub-agents that leverage different AI models for specialized tasks. I built a Gemini research specialist that uses Google’s 1 million token context window for research—and it’s transformed how I gather information during coding sessions. https://lnkd.in/dXnpaAkR

27

3 days ago I shared AgentLint — 10 rules to stop AI agents from drifting during long sessions. Since then I've shipped 4 major releases. Here's what changed: 10 rules → 42 rules across 7 packs AgentLint now auto-detects your stack and activates the right guardrails: 🐍 Python — bare excepts, unsafe shell, SQL injection, dangerous migrations 🎨 Frontend — accessibility checks (alt text, form labels, focus states, touch targets) ⚛️ React — loading states, empty states, lazy loading 🔍 SEO — metadata, Open Graph, semantic HTML, structured data 🔐 Security (opt-in) — blocks Bash file writes that bypass guardrails, catches data exfiltration attempts Full lifecycle coverage AgentLint went from 3 hook events to all 17 that Claude Code supports. New always-active quality rules: - Validates commit messages - Catches dead imports - Warns when error handling gets removed - Injects a self-review prompt at session end - Tracks session length and warns before things drift AGENTS.md support If your project uses AGENTS.md, AgentLint reads it and generates matching config automatically. Installation that just works I dogfooded a fresh install and hit the same PATH issues many developers face with pip on macOS. Fixed it — the resolver now probes 5 locations to find the binary. No more manual PATH hacking. The numbers 42 rules. 741 tests. 96% coverage. All running locally in milliseconds. pip install agentlint agentlint setup If you're running AI agents on production codebases, the question isn't whether they'll drift — it's whether you'll catch it before or after it ships. 👉 https://lnkd.in/eRMqpDHd #AI #ClaudeCode #DevTools #OpenSource #CodingAgents #DeveloperExperience #Python #AgentSafety

7

✴️ Apple Container – Quick Notes   <https://lnkd.in/gVyTEvE9> - On June 9, 2025, during WWDC, Apple pushed the new Container project to GitHub and tagged its first release, v0.1.0.   - The repository was initialized and made public four days earlier, on June 6, 2025.   - Written in Swift and released under the Apache-2.0 license.   - The `container` CLI currently supports `images pull`, `run`, and `push`.   - Each container runs inside a lightweight VM managed by Virtualization.framework.   - Works directly with standard OCI images and connects to any compliant registry.   - Currently supported only on Apple Silicon and requires the macOS 26 beta.   - Rosetta 2 enables x86_64 binaries to run inside containers.   - Documentation cites startup times of under one second. #ContainerizationFramework #traveller #tdi #container #apple

3

1 Comment

I had an absolute blast chatting with Tracy Lee and Danny Thompson on the Leadership Exchange Podcast about what it really takes to build intelligent systems in the AI era. We went deep on: 🤖 The shift from single-model thinking to agentic ecosystems 🧭 Why judgment and evaluation matter more than ever 💼 How AI and Product roles are evolving 🧩 Why data quality and governance quietly make or break AI success 🎯 What the rise of the Chief AI Officer tells us about the future of leadership 🔥 Hot take: AI transformation is 20% tech, 80% culture. If you’ve ever wondered how to evolve your teams, systems, or career in this new AI landscape — this one’s for you. 🎧 Watch here → https://lnkd.in/gABmqvTb What’s your biggest challenge in scaling AI beyond prototypes? #AI #Leadership #Innovation #ProductManagement #DataScience #AIAgents #Engineering

33

2 Comments

Measuring developer productivity is complex. At Meta, the team has been taking a rigorous, data-driven approach and even building new infrastructure to support it. Kudos to Payam, Pavel, and the entire team for this impressive work and presentation. Over the past year, my main focus has been on building AI coding agents, so this really resonates. Check out the section about Devmate at 6:52 in the video to learn more on what I've been up to. A few highlights: - Thanks to Devmate, Meta’s developers are more productive - with Diffs per Developer per Month (DDM) improving by 6–12% (a conservative estimate!). - Devmate tracks AI code attribution at the character level, allowing Meta to know precisely which code was generated by Devmate vs. written by humans.

15

Seeding even simple environments with meaningful data that exercises all flows, especially as systems grow and microservices proliferate, has always been a challenge. It becomes even harder when you need realistic, interconnected datasets that respect business rules across services. That’s why we built datagen - a scalable tool for generating coherent, synthetic data to power local dev, staging environments, benchmarking, testing and more. It lets you define data models declaratively, handle cross-references and generate large datasets with ease. And now it’s open source - give it a go and see if it solves your use case! #PlatformEngineering #TestData #DistributedSystems

34

To me "organizational memory" translates to the all knowing project manager available to every person in the company. What would you do if you could have your own project manager that remembers everything, keeps things on track at all times, tells you about the project risks as soon as they materialize, and not when it's already too late?

6

One of my favorite moments from PDotSF this week was acknowledging something simple but important with the Cursor team. Our engineers use Cursor every day.Their engineers use PagerDuty every day. We’re not showing up only as partners. We’re showing up as customers of each other’s products.That changes the conversation entirely.The future of engineering will be shaped by deeply integrated workflows between humans, agents, and the systems teams trust to build and run the world’s most important software. Really enjoyed the conversation Alexi Robbins 🚀

91

3 Comments

This is a huge update that anyone who cares about workload identity or agentic security should be paying attention to. Kong Mesh is the first and only service mesh to natively act as a SPIFFE identity issuer, to interoperate with an existing SPIRE deployment, or to federate between two. This vastly improves interoperability in hybrid and multi mesh deployments. Great work Kuma team! We'll be sharing more about how this can help solve for modern enterprise security challenges in a future post.

32

WIZARD OF WHIDBEY: Realtor and rising AI Chef 🧑‍🍳 Brandon Gallmeyer https://lnkd.in/d7NT6zuN visited the Cozy AI Kitchen to share a realtor-centric CRM with AI-enhanced capabilities he built in under a week with no recent coding experience. HT 🧑‍🍳 Ross Heise Back Story In elementary school, Brandon did coding clubs and learned Scratch -- but hasn't had an opportunity to do computer programming since that moment. In the first week of September while I was shopping for real estate, I met Brandon via Zillow and was impressed with how he used ChatGPT in returning responses to me that took large amounts of data and compressed them into useful lists for us to go over via email. Then, I went to Whidbey Island to see him and learned about his frustration with existing CRMs and suggested he set up a GitHub account and use AI coding tools to enable him to make his own app. It was only 3 days later that he showed me what he cooked up. This video was taken just two weeks after I first met Brandon. What's Next? IMO Brandon's a heckuva product manager. Plus he's already designed and engineered a beautiful product he's now using on his own. I believe he's one of the first "full stack realtors" out there that's ... under ... 21 🤯 It's clear to me now that there will be many new AI Chefs rising out there in every possible trade -- and a lot of potential for more digital transformation to get unlocked at every imaginable scale. It's an unusual and exciting time for anyone who has the gift of computational thinking. It's now the time of computational making for anyone who knows how to speak machine! --- 50th Episode with Chef 🧑‍🍳 Gallmeyer: https://lnkd.in/d7NT6zuN All 🎂 Cozy AI Kitchen Episodes: https://lnkd.in/g6upvbGX How To Speak Machine (2025 Edition): https://lnkd.in/gC9DGPb8

75

7 Comments

From our CEO Maxime Beauchemin, mind-blowing to read this and think about what this means for the future of software development. "Are we headed toward a software utopia? What does that even look like? The absence of software?"

8

1 Comment

Cut dev iteration time—for humans and AI: Remote build caching with Bazel & Gradle speeds up builds, reduces context switches, and helps all your engineers (carbon- and silicon-based alike) ship faster. ⚡

15

AI for Product Managers There’s a lot of discussion right now around agentic development, but far less around how Product Management effectively interfaces with these emerging AI-native engineering workflows. Appreciate Chris Butler for putting together a practical and grounded approach to solving that gap. https://lnkd.in/gb3e6QYa

22

1 Comment

"APIs are the connective tissue that allow an organization to thrive." Nearly every company I speak with is navigating the same challenge: modernizing their API landscape while preparing for AI-driven systems. The biggest brands want clear guidance on how to govern, scale, and future-proof their APIs as AI becomes more central to how software is built and operated. This conversation with Matthew Gray, Head of Channel Sales at Postman, does a great job exploring what that journey looks like in practice and why APIs sit at the center of it. Full discussion: https://lnkd.in/g8qUX9dt

126

5 Comments