iiinova — where your digital self keeps evolving

Trigger.dev @triggerdev.bsky.social · 21/09/2026

New Trigger.dev projects now open with a "Copy AI agent prompt" button. Paste it into Claude Code or Cursor and your agent goes from an empty repo to a task that's registered and verified in the dashboard, not just a few generated files. How it works ↓

100

Trigger.dev @triggerdev.bsky.social · 17/09/2026

Smart columns are the good part. Point one at a run's payload, metadata, or output with a JSON path: $.𝚘𝚛𝚍𝚎𝚛.𝚝𝚘𝚝𝚊𝚕 as a number $.𝚌𝚞𝚜𝚝𝚘𝚖𝚎𝚛𝙸𝚍 as text $.𝚜𝚝𝚊𝚝𝚞𝚜 as a badge Give it a label and it fills in down the whole list.

100

Trigger.dev @triggerdev.bsky.social · 17/09/2026

Column control landed on the Trigger.dev runs list. Show, hide, and reorder columns, or add a smart column that pulls a single value straight out of a run and shows it for every row. ↓

100

Trigger.dev @triggerdev.bsky.social · 07/09/2026

When a Trigger.dev backlog builds, the only question that matters: is work not starting, or are the runs that start failing? Different problems, different fixes. Now one command tells you which ↓

100

Trigger.dev @triggerdev.bsky.social · 03/09/2026

Define your prompts in code. Override them live when you need to. On Trigger.dev a prompt is an id, a model, typed variables, and a template, and every deploy creates a new version. Override the text or model from the dashboard, no redeploy ↓

100

Trigger.dev @triggerdev.bsky.social · 20/08/2026

Our MCP server does a lot more than deploy and trigger tasks now. Your coding assistant can chat with your deployed agents, manage prompt versions, and pull a health report. Straight from Claude Code or Cursor. ↓

110

Trigger.dev @triggerdev.bsky.social · 18/08/2026

Two views on the same data. The dashboard tells you what you spent: cost over time, cost by model, tokens, latency across the whole workload. The trace tells you why. Open a call for the model, the full message thread, every tool call, and the prompt behind it.

100

Trigger.dev @triggerdev.bsky.social · 18/08/2026

You could always see what a task did. Now you can see what it spent. Every LLM call your Trigger tasks make becomes a span in the trace. One flag, 𝚎𝚡𝚙𝚎𝚛𝚒𝚖𝚎𝚗𝚝𝚊𝚕_𝚝𝚎𝚕𝚎𝚖𝚎𝚝𝚛𝚢, on any Vercel AI SDK call. Nothing to install. Whole AI bill, or any single call, in the trace ↓

120

Trigger.dev @triggerdev.bsky.social · 13/08/2026

Every turn is a span in the dashboard: the prompts, the responses, the tool calls, how long each took. An AI metrics dashboard ships with every project too: spend, tokens, latency percentiles, cost by model. No instrumentation to write.

100

Trigger.dev @triggerdev.bsky.social · 13/08/2026

𝚌𝚑𝚊𝚝.𝚊𝚐𝚎𝚗𝚝 is a chat backend where every conversation runs on its own real machine. It boots on the first message, runs as long as the work takes, and keeps its memory between turns. Here's how one is put together, with Trigger ↓

100

Trigger.dev @triggerdev.bsky.social · 12/08/2026

Why we built it: - No timeouts. 1 in 20 turns runs over 36 minutes in production - Refresh mid-response and the stream picks up where you left off - Waiting is free. An agent can wait overnight for a human approval Arena.ai runs Agent Mode on it at scale. It went GA in July and is Apache 2.0

000

Trigger.dev @triggerdev.bsky.social · 10/08/2026

Introducing chat agent Build durable AI chat experiences that run on a machine with no timeouts and keep streaming through refreshes and crashes. The machine sleeps when nobody's typing and wakes where it left off, without you managing any state.

100

Trigger.dev @triggerdev.bsky.social · 07/08/2026

Every conversation gets its own computer. Launching Monday.

000

Trigger.dev @triggerdev.bsky.social · 06/08/2026

Star any page in the Trigger dashboard and it pins to Favorites at the top of the side menu, filtered views included. You can also rename favorites, hide the items you never open, and drag the menu into the order you want. trigger.dev/changelog/d...

000

Trigger.dev @triggerdev.bsky.social · 15/07/2026

The brief: build a chat agent that changes how people interact with information. Trigger.dev runs the orchestration and AI agents. ClickHouse is the real-time data layer underneath.

100

Trigger.dev @triggerdev.bsky.social · 15/07/2026

Applications for our hackathon close tomorrow (16 July). Co-hosted with our friends at Clickhouse. One week to ship a production-quality AI chat agent, free cloud credits for both platforms if you get in. With a €10,000 prize pool, hardware, cloud credits and swag.↓

100

Trigger.dev @triggerdev.bsky.social · 09/06/2026

Every booking on Cal.com fans out into webhooks, emails, SMS, calendar APIs. Salesforce events for enterprise, billing, and fraud checks. All of it runs on Trigger. Morgan Vernay from the Foundation team on how it works ↓

100

Trigger.dev @triggerdev.bsky.social · 29/05/2026

We just hit ⭐ 15,000 GitHub stars. ❤️ Thank you to our community for your ongoing support!

000

Trigger.dev @triggerdev.bsky.social · 15/05/2026

Your tasks can now connect to private resources in your AWS VPC. RDS, ElastiCache, internal APIs, self-hosted services. No public endpoint, no IP allowlist, no VPN. Over AWS PrivateLink ↓

100

Trigger.dev @triggerdev.bsky.social · 13/05/2026

The list and individual error page filter by task version. The chart stacks errors by version. The shape of a fix landing: a tall bar that tapers off the moment `𝚟𝟷.𝟺.𝟽` ships.

110

Trigger.dev @triggerdev.bsky.social · 13/05/2026

Replay every run in an error group with one click. For when a bad deploy nuked 200 jobs and you've just shipped the fix.

110

Trigger.dev @triggerdev.bsky.social · 13/05/2026

Every error has a status: unresolved, resolved, or ignored. Mark resolved when you've shipped the fix. Ignore for hours or days when you're not ready to deal with it. Bulk actions on the list let you triage many at once.

110

Trigger.dev @triggerdev.bsky.social · 13/05/2026

Alerts fire once per error group, not once per failed run. (Slack timestamps use `<!𝚍𝚊𝚝𝚎^>` tokens, so London + SF in the same channel render their own time.)

100

Trigger.dev @triggerdev.bsky.social · 13/05/2026

Failed runs get fingerprinted by error type and message, with dynamic parts (IDs, timestamps) stripped. 200 instances of `𝚄𝚜𝚎𝚛 𝚊𝚋𝚌-𝟷𝟸𝟹 𝚗𝚘𝚝 𝚏𝚘𝚞𝚗𝚍` and `𝚄𝚜𝚎𝚛 𝚡𝚢𝚣-𝟽𝟾𝟿 𝚗𝚘𝚝 𝚏𝚘𝚞𝚗𝚍` collapse into one row with a count and a timeline.

100

Trigger.dev @triggerdev.bsky.social · 13/05/2026

Errors: find and fix your bugs faster. You can now quickly track down what’s causing your runs to fail with error alerts. Then bulk replay when you’ve shipped the fix. ↓

110

Trigger.dev @triggerdev.bsky.social · 21/04/2026

Send from React in a few lines. `𝚞𝚜𝚎𝙸𝚗𝚙𝚞𝚝𝚂𝚝𝚛𝚎𝚊𝚖𝚂𝚎𝚗𝚍` wires up any button, form, or chat input to a running task. Typed all the way from the click to the task.

100

Trigger.dev @triggerdev.bsky.social · 21/04/2026

Need a human in the loop? `.𝚠𝚊𝚒𝚝()` suspends the task entirely. The process gets freed. Zero compute cost while it waits. Data lands, task resumes exactly where it left off. Timeout up to 7 days.

100

Trigger.dev @triggerdev.bsky.social · 21/04/2026

Cancel buttons, finally the easy way. Register a `.𝚘𝚗()` listener for a cancel stream. User clicks stop, you abort the @aisdk completion mid-stream. No polling. No external pubsub. No race conditions.

100

Trigger.dev @triggerdev.bsky.social · 21/04/2026

The pattern that unlocks everything: `𝚜𝚝𝚛𝚎𝚊𝚖.𝚘𝚗(𝚑𝚊𝚗𝚍𝚕𝚎𝚛)` Define a typed stream once. Listen for messages in the background while your task works. Your agent is researching. Your user types "actually, focus on pricing." The task picks it up mid-run and adjusts.

Code snippets define a message stream system with handlers for user instructions and a research task managing context and messages.

100

Trigger.dev @triggerdev.bsky.social · 21/04/2026

You can now chat with your running tasks. Input streams: send typed data INTO a Trigger.dev task while it's executing. - Cancel signals for AI generations - Course-correct agents mid-run - Approval gates that free compute while they wait Shipped in v4.4.2 ↓

100

Trigger.dev @triggerdev.bsky.social · 15/04/2026

→ Dashboards Every project ships with a pre-built one: run volume, success rates, failures, costs, versions. Build custom ones on top with big numbers, charts, and tables. Filters apply across every widget at once.

100

Trigger.dev @triggerdev.bsky.social · 15/04/2026

→ Query. Ask "what are my p95 durations for the chat task?" and the AI writes the TRQL, runs it on ClickHouse, renders the chart. Or write the SQL yourself.

100

Trigger.dev @triggerdev.bsky.social · 15/04/2026

→ Our @vercel integration is live. Push code, tasks deploy automatically. Env vars sync both ways. Atomic deployments gate Vercel's promotion until your tasks are ready, so your app never goes live with a mismatched task version. No 𝚝𝚛𝚒𝚐𝚐𝚎𝚛.𝚍𝚎𝚟 𝚍𝚎𝚙𝚕𝚘𝚢, no CI/CD workflow.

110

Trigger.dev @triggerdev.bsky.social · 15/04/2026

In case you missed it, here are some of the things we shipped in March: → Native @vercel integration → Query & Dashboards (ask in English, get SQL) → 5x throughput from a Bun rewrite → New MCP tools, TTL defaults, 𝚜𝚢𝚗𝚌𝚂𝚞𝚙𝚊𝚋𝚊𝚜𝚎𝙴𝚗𝚟𝚅𝚊𝚛𝚜 Full recap ↓

110

Trigger.dev @triggerdev.bsky.social · 13/04/2026

3 tasks, each in its own container: 𝚑𝚊𝚗𝚍𝚕𝚎-𝚙𝚛: fetches the diff, calls Claude, posts a single review comment (HTML anchor 𝚊𝚒-𝚛𝚎𝚟𝚒𝚎𝚠-𝚜𝚞𝚖𝚖𝚊𝚛𝚢 prevents duplicates on re-runs) 𝚑𝚊𝚗𝚍𝚕𝚎-𝚒𝚜𝚜𝚞𝚎: Claude classifies, parses JSON labels, applies via GitHub API 𝚑𝚊𝚗𝚍𝚕𝚎-𝚙𝚞𝚜𝚑: Claude summarizes commits in Slack

110

Trigger.dev @triggerdev.bsky.social · 13/04/2026

GitHub sends a webhook. 60 seconds later, Claude has reviewed your PR diff, labeled your issue, and posted a deploy summary to Slack. Built with HookDeck + Trigger.dev + Claude ↓

110

Trigger.dev @triggerdev.bsky.social · 01/04/2026

We're heading to AI Engineer Europe in London! April 8-10 | QEII Centre, London UK | Booth G6 Come and chat with us If you're building AI agents, workflow automation, or background jobs. We'll be doing live demos, sharing what we're building, and handing out swag. See you there!

120

Trigger.dev @triggerdev.bsky.social · 12/03/2026

Fun fact: this was also our most requested feature, with 354 votes.

100

Trigger.dev @triggerdev.bsky.social · 12/03/2026

Deployments now cross-link on both sides. Trigger adds deployment checks to your Vercel deploys so you can see task build status without leaving Vercel. Each Trigger deploy links back to the matching Vercel deploy. No more tab-switching to match app deploys to task deploys.

110

Trigger.dev @triggerdev.bsky.social · 12/03/2026

Env var sync works both ways: Vercel → Trigger: pulls env vars per env (prod/staging/preview) before each build. Trigger → Vercel: keys like TRIGGER_SECRET_KEY sync back automatically. No more copy‑pasting. Control sync per variable on the env vars page.

110

Trigger.dev @triggerdev.bsky.social · 16/02/2026

Cursor CLI outputs NDJSON. We parse it line by line, push events into Realtime Streams v2, and render each one as a row in a React terminal component.

100

Trigger.dev @triggerdev.bsky.social · 16/02/2026

Run Cursor's headless CLI agent inside a Trigger.dev task and stream its output live to your app's frontend. This open source demo: Next.js + Trigger. ~1,000 lines of code in total. Here's what's interesting about the architecture ↓

100

Trigger.dev @triggerdev.bsky.social · 05/02/2026

Pattern 5: Evaluator-Optimizer One model generates an output, another evaluates it, and the task loops until quality criteria are met. This is an iterative system. You need recursion, clear approval thresholds, telemetry, and a hard stop on retries.

100

Trigger.dev @triggerdev.bsky.social · 05/02/2026

Pattern 4: Orchestrator-Workers A central agent breaks down a task and delegates to worker agents. This is a Distributed System. You need queues, retries, and error handling. @triggerdotdev provides this out of the box.

100

Trigger.dev @triggerdev.bsky.social · 05/02/2026

Pattern 3: Parallelization "Vote" on the best answer from 3 models. Challenge: Node.js event loop blocking or memory limits. Fix: Fan-out execution. Trigger 5 sub-tasks in parallel, gather results when all complete.

100

Trigger.dev @triggerdev.bsky.social · 05/02/2026

Pattern 2: Routing Classify input -> route to specialized model (e.g., Opus 4.5 for code, Gemini-2.5-flash for text). Challenge: managing differing latencies. Fix: Async background jobs that handle the routing logic independently.

100

Trigger.dev @triggerdev.bsky.social · 05/02/2026

Pattern 1: Prompt Chaining Output of one LLM call becomes input for the next. Challenge: If step 4/5 fails, you don't want to restart from step 1 (costly). Fix: Automatic checkpointing saves the result of every step.

100

Trigger.dev @triggerdev.bsky.social · 30/01/2026

Shared queue keeps Firecrawl requests under limit across all concurrent analyses. Progressive model escalation: gpt-4o-mini → gpt-4o → gpt-4o + markdown fallback. Trigger handles retries automatically.

100

Trigger.dev @triggerdev.bsky.social · 30/01/2026

Two chains run in parallel via batch triggers which cut analysis time in half. Wait tokens pause execution for human review with no webhooks needed:

100

Trigger.dev @triggerdev.bsky.social · 30/01/2026

Tierly uses Trigger to orchestrate 10+ AI models for competitive pricing analysis. Each analysis: dozens of scraping tasks, human review gates, and real-time progress updates. How they built it 🧵

100