ai-workflows
112 posts tagged ai-workflows.
- Amplitude's Wave and the agent loop that starts before anyone asks for a feature
- LLMON puts markup closer to the model
- ReTrace turns repeatable agents into code paths
- Local AI on 16GB VRAM is a scope problem, not just a model problem
- What Changes When You Treat an LLM as a Pair, Not a Vending Machine
- Local GUI agents need disposable desktops, not prettier demos
- What 'AI accelerating AI research' actually looks like inside a lab
- Gemini Is Moving Closer to Google Business Profiles
- Cognitive symbionts shift the agent question back to the human
- Context is the missing layer in AI code review
- LifeVal puts AI evals closer to real paperwork
- Local AI is becoming the quiet default for private workflows
- Unlimited AI Tokens Are a Process Test, Not a Coding Strategy
- Chrome’s Gmail Autofill Is Small, Useful, and Privacy-Sensitive
- LangChain’s tiny core releases are really about state discipline
- OpenAI and ServiceNow move agents closer to enterprise work queues
- What OpenAI's Ropes & Gray diligence build actually automates
- Hidden AI Opinions Can Steer Expert Analysts
- Voice-first rehearsal is a better AI workflow than slide generation
- DexPort makes robot hand data collection less robotic
- Inbox agents need labels before models
- AI payoff outside tech is a workflow problem, not a model problem
- AI prose gets hard to read when it removes friction
- The wrong way to count AI job losses in media
- AI enablement is becoming curriculum ops
- Claude Duet tests the proactive assistant, not a new chatbot
- OpenAI’s Dots demo turns bug triage into an agent workflow
- RealPage’s AI training workflow is the useful kind of boring
- AI makes weak marketing dashboards fail faster
- Claude Code turns smart TV cleanup into a weekend mod
- SERP network data is becoming an SEO research surface
- Legal AI trust starts with workflow, not model magic
- Sphinx turns AI code shipping into a comprehension check
- Themeable Mermaid SVGs solve a small but real AI docs problem
- LangChain 1.6.12 fixes a small streaming metadata leak
- StepFun’s agent phone is a bet against the app grid
- Agreement review is where legal AI gets real
- The Case for Making Research Agents Forget Their History
- PDFs can rank, but they are still a weak default for SEO
- Self-Evolving Agent Harnesses Need Change Control More Than Hype
- Build a Decision Model Before You Automate the Decision
- Oracle’s Codex story is about killing the report backlog
- README testing is cheap agent evaluation for humans
- What ExxonMobil's Deception Case Teaches AI Builders About Source Trust
- LLMs belong in the feature factory, not always in production
- OnTrack watches agent trajectories before the bill is paid
- Asana’s browser-agent test points to the real AI cost story
- LegalOn’s Codex cost cut was routing, not magic
- What Sophos actually automated to cut threat response from 38 minutes to 89 seconds
- GPT-6 and Intelligent UI: What OpenAI Actually Announced
- AI is better as the SEO audit explainer than the SEO auditor
- AI compresses the domain-to-website workflow
- Agent memory is not a substitute for readable docs
- Opus 5.5 tips are really workflow design tips
- SaaS Is Becoming the Control Layer Around Models
- A simulated canvas turns vision models into operators
- Chainalysis’s AI tracing claim is a workflow story, not magic attribution
- Claude Design and the Return of the Design Spike
- Karpathy’s Aircraft Manual Prompt Is Really a Spec for Better AI Output
- OpenAI’s Python SDK is getting more agent-shaped
- MAICON’s Real-Time Podcast Move Is a Content Ops Signal
- The Harness Is the Model: What 'Meta-Skills for Agent Harness Design' Actually Shows
- Black-box attribute alignment is a sampler, not a fairness wand
- The useful part of Roetzer’s architect-orchestrator-apprentice AI work model
- Agent control failures are moving from demo risk to operating risk
- Drawgent puts a coding agent on an Excalidraw canvas: what a visual work surface actually changes
- Keeping programming enjoyable when LLMs write the first draft
- Qwen 27B on a 4090 is a useful reminder about local AI demos
- What One Developer Learned From a Month Without AI Tools
- AI Agents Make Audience Data Debt More Expensive
- CliffCompaction makes long coding runs cheaper by refusing to summarize
- Jev shows why science workflows need semantic evals, not just final-answer grading
- AI adoption is the easy checkbox. Workflow adaptation is the actual job
- AI writing is useful until it starts doing your thinking
- AI posters get better when the model stops being the designer
- Hex, GPT-6 Astra, and the shift from answers to visual reports
- LangChain 1.4.2 fixes a small but real agent reliability problem
- Jev is a decision model, not another chatbot
- Claude as a transfer-code assistant for domain portfolios
- CareMirror puts caregiver consent at the center of dementia AI
- Turn repeat marketing work into tools, not just prompts
- AI sadness is product feedback, not just backlash
- Conversational XAI works best when it is a control surface, not a chatbot
- The marketing AI stack is too full now
- Codex as a lab scout for antimicrobial search
- PPC Automation Needs Guardrails, Not Blind Trust
- Browser agents are becoming practical comment analysts
- Pick the hospital automation work before picking the bot
- Procedural Graphs give agents a memory of what to do, not just what happened
- What ChatGPT Images 2.5 Changes for People Who Actually Ship Images
- AI Made the First Draft Free. The Bottleneck Moved Downstream.
- OpenAI’s journalism program stretches from classrooms to newsrooms
- The real lesson in a 90% Claude Code token cut
- AI workflows should create new work, not just faster tasks
- Compliance LLMs need different workflows for passports and DPIAs
- Codex over Claude is a workflow signal, not a verdict
- Alzheimer’s surgery claims need evidence before amplification
- A one-line Hacker News item is not enough context
- RingCentral’s AI-native work story is really about the handoff
- OpenAI’s small business push is really a workflow bet
- ChatGPT onboarding starts with a real task, not a perfect prompt
- “Ask an LLM” Is Not an Answer to Every Question
- TPG’s ChatGPT rollout targets the boring costs of diligence
- Timestamp drift is the quiet ASR failure that breaks real workflows
- An aviation headline in the AI feed is a pipeline problem
- Agentic coding works best when the repo has rails
- Entity gap patching: the pSEO maintenance loop most teams skip
- Marketers are still vibe-checking prompts. Frontier devs run evals before lunch.
- Stop Vibe-Checking New Models. Build a 50-Prompt Eval Set Instead.
- The mechanism matters: making AI competitive analysis auditable
- Why I Stopped Trusting My Own Prompts (And Started Logging Them)
- Why I Stopped Trusting AI Demos and Started Timing My Own Workflows