Enter the site
Sound unavailable

This is the first Caught Up, a weekly page from Bluebird for people who build with AI: mostly software, and the ads, video and sound that go out with it. If something doesn’t change what you’d use on Monday, it isn’t here.

We build with AI every day, and there is more news than anyone can read, so each Wednesday we keep only what changes how you build. Every issue: the 30-second version, at most three big stories, one thing to do, and what we shipped, with the tools we used. This first issue starts with the kit, the five tools that turn most news into a small upgrade. From next week it’s just the news, about four minutes.

The 30-second version

Part one · Start here

Building with AI is five tools and a way of working

Most of what’s announced in a week is a new version of one of these. Get them in place once, and the news becomes small upgrades.

04Instructions fileHow your project works
01 + 02Coding agent, driven by a modelReads the repo, runs commands, makes the change
03 · MCPThe plug into your database, tracker, docs and browser
05Tests and evalsIs the result right?
How the five fit together. You sit at both ends: you write the instructions and you review the result.
  1. 01

    A coding agent

    A tool that reads your repo, runs commands and makes the change while you review. The big ones copy each other within weeks: pick one and learn it properly.

  2. 02

    Two models: a daily driver and a cheap one

    A strong model for thinking and a small, fast one for bulk work. You rarely need the top shelf.

    TierAnthropicOpenAIGoogle · Meta
    Top shelfFable 5.2GPT-6 AstraGemini 4 Carbon
    Daily driverOpus 5.5GPT-6.1 SolGemini 4 Argon
    Cheap and fastHaiku 5.5GPT-6 LunaMuse Ember (Meta)
  3. 03

    MCP, the standard plug

    The Model Context Protocol connects an agent to your database, issue tracker, docs and browser. Every major lab supports it. Learn to add a server to your agent instead of writing one-off integrations.

  4. 04

    An instructions file

    A plain text file in your repo that tells the agent how the project works: the commands, the conventions, what not to touch. It is the cheapest quality gain there is.

  5. 05

    Tests, and a small eval set

    An agent is as trustworthy as the checks around it. For code, that is your test suite. For a model inside a feature, keep about 20 real examples with known good answers and rerun them after any change.

One task, start to finish

StepWhat you do
1 · PlanDescribe the result you want and ask for a plan before any code. Fixing a plan is cheaper than fixing code.
2 · Let it workThe agent edits, runs the tests and fixes what fails. Tell it what is wrong rather than taking over.
3 · CheckTests and examples say whether it works. If there are none, ask for them first.
4 · ReviewRead every change as you would a colleague’s pull request. You own what ships.
5 · Write it downWhen the agent gets something wrong twice, add a line to the instructions file.

Leave these until a real problem asks for them

  • Agent frameworks
  • Fine-tuning
  • Vector databases
  • Prompt courses
  • Leaderboard arguments

Part two · The week, 10 to 16 November

One new model, and it’s the cheap one

The top of the table didn’t move. The news is lower down, where most of an agent’s work happens.

Where the models stand today

Intelligence Index score, higher is better. The right-hand column is what one benchmark task cost to run.

New this weekAlready out

ModelScoreCost / task
Claude Fable 5.265$26.54
Gemini 4 Carbon60$5.48
Claude Opus 5.559$10.04
GPT-6 Astra57$6.24
GPT-6.1 Sol55$1.27
Claude Sonnet 5.555$10.02
Gemini 4 HydrogenNew54$3.16
GPT-6.1 Terra51$0.96
Gemini 4 Argon50$4.97
Claude Haiku 5.536$0.41
Muse Ember36$0.14
Source: Artificial Analysis, read 17 Nov 2026, each model at its highest effort.

New model · 12 Nov · Google

Try it for routine agent work

Gemini 4 Hydrogen: Argon’s score at a lower price

Index score. Argon scores 50
54
Per million tokens in and out
$1.50 / $7.50
Per index task. Argon cost $4.97
$3.16

Hydrogen does the edits, test runs and tool calls while Carbon or Argon does the thinking. Antigravity’s new Orchestrator works that way, and Google says it came close to Carbon alone with 24% less quota. It’s in the Gemini API (with a free tier), Antigravity and GitHub Copilot.

What to doIf an agent does routine edits on a frontier model, run your examples on gemini-4-hydrogen. Keep the planning on the big model.

New API · 11 Nov · Google

Try for routing and checks

Gemini Decisions API: a model that only answers the question

Per million tokens in. Nothing for output
$0.10
Questions in one request
1,000
End to end, by Google’s count
150–250 ms

Gemini Decision 1 writes no text. Send an input (text, images, audio, video or PDF) and your questions; it returns each answer with a probability. That is what a router or a pass/fail grader needs.

What to doIf a model call only picks a route or a pass/fail, try it here, checked against examples a person has labelled.

Tool · 12 Nov · Anthropic

Try on a many-file chore

Code Mode in Claude Code: one script instead of many tool calls

Claude writes a short JavaScript program that calls its tools, instead of calling them one by one. It’s experimental: terminal only, on Anthropic’s API, with the 5.5 models and Fable 5.2.

What to doSet CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 and try one many-file chore, such as a rename. Compare time and tokens with a normal run.

Beyond code · Video, images, sound

One release for the things people hear

No big video or image model this week. If you work with calls or interviews, this one matters.

Speech model · 10 Nov · ElevenLabs

Switch if you transcribe calls

Scribe v3: fewer wrong words, and it knows who spoke

Fewer word errors than Scribe v2
27%
Per hour of audio. $0.22 live
$0.20

Speech to text for recordings, with a Live version for realtime. ElevenLabs says it labels speakers better than any model it tested, and it takes a list of terms to expect, such as product names.

What to doIf you transcribe calls, run last week’s hardest recording through v3, with your product names as terms.

Also this week · Tools and heads-ups

Smaller things, quickly

Worth knowing, without a story each.

Tools that shipped

Safe to skip

  • “OpenAI’s new low-cost model” headlines. That was September’s GPT-6.1 Sol. OpenAI released no model this week.
  • “ChatGPT Wallet”. A name found in an app build. Nothing announced.
  • Qwen4-Max Preview. No API price and no weights yet.

Practice · How to work

One habit worth copying

Tools change every week. How you work with them changes slowly.

Research · 13 Nov · Anthropic

Apply the idea

Grade with yes/no questions, and test what you ship

One model, scored without and with its app’s system prompt
60% vs 94%

Anthropic’s write-up on safety evals fits any eval. Break “is this good?” into yes/no questions. Check the grader against answers a person marked. Run each case more than once. Test the setup you ship, prompt included.

What to doTake the 20 examples from your eval set and rewrite each “good answer” as three or four yes/no checks.

If you do one thing this week

Move one routine step to a cheaper model, and let your examples decide.

Routine steps rarely need the top shelf. With your examples saved, switching is a test with a clear answer.

Read the prompt
Help me test moving one step of my AI feature to a cheaper model.

Step: [what it does, in one sentence]
Model today: [model ID]   Cheaper model to try: [e.g. gemini-4-hydrogen]

1. Find where this step calls the model, and the examples or eval set for it. If there are none, collect 20 real inputs, show them to me and stop.
2. Write what a good result must contain as yes/no checks for each example.
3. Run every example three times on both models. Print the pass rate, cost and time side by side.
4. Show me what failed on the cheaper model.

Do not switch the model in the app. Ask me before you guess at anything.

You can stop here. You’re caught up.

From our own bench

What we shipped, and what we used

We build with the same kit. This is everything we launched in the last three weeks.

  • Magic Weather

    In Google Play since 9 November and the App Store since 10 November. Hold your phone up to the sky and the app’s picture of it matches. No ads, no account.

  • Magic Sudoku

    Version 1.0.4 is in both stores, with a lesson on notes and hints chosen for the board in front of you. On the web, players now set puzzles for each other and race on opt-in Purist leaderboards.

  • bluebird.tech

    Our new site went live on 27 October with its own read-only MCP server. Add https://mcp.bluebird.tech/mcp to your agent to search our work and case studies.

A still from the Magic Weather film: a phone showing Cape Town’s forecast in front of a beach and mountains under a partly cloudy sky
From our Magic Weather film: a generated sky behind a real recording of the app.
A sudoku box with a small 2 noted in the corner of two cells
From How notes work, Magic Sudoku’s one-minute lesson.

The tools behind them

JobWhat we used
BuildingClaude Code, with an instructions file in every repo
ReviewCodex, then GitHub Copilot, before a change merges
AppsExpo and React Native: one codebase for iPhone, Android and the web
Sudoku hintsOur solver proves each step; GPT-6.1 Terra, picked by testing models on our own examples, chooses one and words the nudge.
MCP serverThe official TypeScript SDK, read-only by design
FilmsMade from code. Skies by Gemini Omni Flash, sound by ElevenLabs

The next one

Next Wednesday

Caught Up, every week

Get the next issue by email.

You’ll get each new issue, and now and then other news from Bluebird. Unsubscribe anytime. Privacy notice.

Rather not give an email? Follow Bluebird on LinkedIn, where each issue is posted.

Caught Up is written by Bluebird Technologies. Magic Weather and Magic Sudoku are our own apps. Next issue: Wednesday 25 November.

Figures were read on 17 November 2026: scores and cost per task from Artificial Analysis, prices from each company’s own pages. The facts come from the linked sources; the verdicts and “what to do” lines are our judgment.