Opus 5.5 + Jev: The Complete Setup (10x Your Output)

TL;DR: How to set up, connect, and run Opus 5.5 + Jev for cheaper, faster, and more productive AI workflows.

I haven't seen anybody else on the timeline talk about this.

You can combine Opus 5.5 + Jev to build AI workflows that are faster, cheaper, and far more reliable than running everything through just one model.

The crazy thing is, it's actually quite easy to set up and only takes a few minutes to get running.

In this article, I'm going to cover everything you need to know about how to build and use this elite AI system:

• Intro to the Powerful System
• Connecting Jev + Opus 5.5
• How to Build Perfect Workflows
• Example Workflows
• Pro Tips

Let's get right into things:

Intro to Jev + Opus 5.5

At its core, this system runs Opus 5.5 for deep reasoning tasks and routes any smaller tasks through Jev for cheap, fast decisions.

You get the best of both worlds: deep reasoning from Opus and efficiency from Jev.

Jev Handles the Judgments

Jev is a pure decision-making model.

You give it two things:

1. The state: whatever it's looking at (an email, a tweet, a task, a document)
2. The questions: what you want it to judge/score

With this info, Jev can return probabilities and confidence scores (you'll see how this comes in handy in a second).

Jev answers three types of questions:

• Choice: pick one option from a list
• Score: rate something on a scale of [1-10]
• True/false: is [x] statement true?

Opus 5.5 Handles the Thinking

Opus 5.5 is the best "thinking" model in the world right now.

I like to use it for:

• Writing and editing
• Research
• High-level strategy
• Coding, building tools, scripts, and automations

The only downside is that Opus 5.5 is quite expensive when run daily and on its own.

By adding Jev on top, Opus only sees what actually needs it.

For example: Let's say you're running an Email triage workflow. Instead of having Opus scan thousands of messages from your inbox, Jev can score them by priority and show Opus only the 5 emails worth replying to.

Why the Combination Works

The system is essentially:

Jev judges → Opus thinks → Code executes on the backend

1. Jev sorts, scores, filters, and ranks all the data/context coming in
2. Opus 5.5 does the high-leverage work
3. Code carries out the actions: archive, label, schedule, send

By using this system, your outputs are:

• Faster: hundreds of decisions in seconds (Jev)
• Cheaper: Opus only consumes tokens on what matters
• More reliable: Jev returns structured answers

It's quite easy to connect the two:

Connecting Jev + Opus 5.5

Step-by-step roadmap on how to route your workflows through both models:

Step 1: Test Jev in the Playground

This is a good low-friction way to test Jev before committing to connecting it to Claude.

You can head to https://jevplayground.com/ and test Jev immediately.

Send a couple of sample prompts here to get a feel for how Jev outputs.

You'll see every answer come back at once, with probabilities and confidence scores.

Step 2: Get Your API Key

Once you've tested Jev for your workflow (let's say Email sorting), grab an API key so we can connect to Claude.

Head to console.typesafe.ai/keys and create a key.

Then add it to your environment so Claude Code can use it:

1export TYPESAFE_API_KEY="your-key-here"

Step 3: Set Claude Code to Opus 5.5

Open Claude Code in the terminal and run /model to select Opus 5.5.

Step 4: Install the TypeSafe Skill

This is a key step. TypeSafe has a skill pack that teaches Claude Code exactly how Jev works.

How to interact with Jev, etc.

Run these two commands in your terminal to install the correct skills:

1claude plugin marketplace add typesafe-ai/skills
2claude plugin install typesafe@typesafe-ai

Restart Claude Code once it's installed.

Step 5: Connect Your Apps

The workflows I'll show you in Section III pull from your inbox, calendar, and notes. So, make sure to connect the apps you want Opus to work with (Gmail, Google Calendar, Notion, Slack) through Claude's connectors.

Step 6: Running Your First Test

The prompt below will run your first cheap tests through your TypeSafe API Key:

1FIRST RUN PROMPT
2
3Using the TypeSafe skill, help me build an AI productivity system
4where Jev handles fast decisions and you (Opus 5.5) handle the deep
5work.
6
71. Ask me what tasks eat most of my day (email, research, content,
8   planning, etc.)
92. For each one, identify which steps are simple judgments (sort,
10   score, filter, yes/no) that Jev should handle, and which need
11   real reasoning from you.
123. Run a few cheap test queries with my TYPESAFE_API_KEY to check
13   the Jev questions work.
144. Propose the first workflow to build, and walk me through it
15   before writing any code.

How to Build Perfect Workflows

If you want to be successful with routing tasks through both models, there are a few general principles you need to apply to get the best possible outputs:

1. Map the Workflow Before You Automate It

Before Opus writes a line of code, break the task into steps and label each one:

1EXAMPLE: CLEARING YOUR INBOX
2
3Pull unread emails .............. Action (code)
4Is this urgent? ................. Judgment (Jev)
5Does it need a reply? ........... Judgment (Jev)
6Archive the junk ................ Action (code)
7Summarise what matters .......... Thinking (Opus)
8Draft replies ................... Thinking (Opus)
9Send after approval ............. Action (code)

2. Write Atomic Questions

Every Jev question should be very specific and check only one thing. Remember, Jev is not a text-output model; it can only give yes/no answers and a confidence score before routing to Opus.

1BAD:  Is this email important?
2
3GOOD: Choice: Urgent, needs reply, FYI, or ignore?
4      True/false: Sent by a real person?
5      True/false: Asks me to take an action?
6      Score: Sender importance (low, medium, high)

3. Give Jev the Right Context

Context is king in this system.

4. Route by Confidence

1High confidence → code acts automatically
2Medium confidence → Opus takes a closer look
3Low confidence → flagged for you

Step 5: Keep Everything in One File

Have Opus put every Jev question and threshold in a single config file, and log every decision with its confidence score. When something goes wrong, you can easily change the workflow.

Step 6: Test Small, Then Schedule

Test your questions in the Playground on a few real examples. Once successful, THEN scale to a full automation inside Claude Code.

Example Workflows

A few sample workflows so you can get some ideas of what the system is capable of:

Workflow 1: Inbox Triage + Management

What Jev judges (per email):

• Choice: Ranks emails as urgent, needs reply, or ignore
• True/false: Sorts if an email is from a real person (not automated)?
• True/false: Does this ask [me] to do something? (like reply)
• Score: How important is the sender? (low / medium / high)

What Opus 5.5 does:

Reads only the urgent and needs-reply emails, summarises each in one line, and drafts replies in your voice from a Claude Skill for you to approve.

1INBOX TRIAGE PROMPT
2
3Using the TypeSafe skill, build an inbox triage workflow for my Gmail.
4
51. Pull unread emails from the last 24 hours.
62. For each email, ask Jev:
7   - Choice: urgent, needs reply, FYI, or ignore
8   - True/false: sent by a real person (not automated)
9   - True/false: asks me to take an action
10   - Score: sender importance (low, medium, high)
113. If Jev is highly confident an email is "ignore", archive it.
12   Label FYI emails. Flag anything with low confidence for my review.
134. For urgent and needs-reply emails, you (Opus 5.5) write a
14   one-line summary and draft a reply in my tone. Do not send
15   anything without my approval.
165. Give me a short digest: what was archived, what needs me, and
17   the drafts.
18
19Put all Jev questions and confidence thresholds in one config file
20so I can review them.

Workflow 2: Research Filter

A workflow to get deeper, better-curated research:

(works for any topic)

1RESEARCH FILTER PROMPT
2
3Using the TypeSafe skill, build a research filter.
4
5My focus areas: [e.g. AI agents, crypto x AI, trading automation]
6
71. Take the list of links or documents I give you (or pull them
8   from my saved Notion page).
92. For each item, ask Jev:
10   - Score: relevance to my focus areas (low, medium, high)
11   - True/false: contains genuinely new information
12   - True/false: has a specific, actionable takeaway
13   - Choice: news, tutorial, opinion, or research
143. Combine the answers into a single ranking. Weight relevance
15   twice as heavily as the other factors.
164. Read only the top 5 in full and write me a one-page brief: key
17   points, what's new, and what I should do with it.
18
19Show me the full ranked list too, so I can see what was cut.

Workflow 3: Content Grader

Such a valuable workflow for content creators.

You can produce exceptional content with this (and of course edit the filters from Jev as needed):

What Jev filters (per hook or content draft):

• Score: How clear is the main idea?
• Score: How specific is it (vague vs concrete)?
• True/false: Could this have been written by anyone, about anything?

Opus can then come in and edit, tweak, and actually write the content in your voice by pulling from a skill file.

1CONTENT GRADER PROMPT
2
3Using the TypeSafe skill, build a content grader for my hooks and
4drafts.
5
61. Take the list of hooks or drafts I paste in.
72. For each one, ask Jev:
8   - Score: clarity of the main idea (low, medium, high)
9   - Score: specificity (vague to concrete)
10   - True/false: creates curiosity
11   - True/false: generic enough that anyone could have written it
123. Rank them all and show which criteria each one failed.
134. You (Opus 5.5) rewrite the bottom half, fixing only what failed.
145. Run the rewrites back through Jev and show me before vs after.

Pro Tips

• Upload as much context as necessary for Opus to create skills for your workflows once Jev filters. Skills make this system a lot smoother.
• You can use Jev to conduct a final pass check on Opus' output. (so the workflow becomes Jev → Opus → Jev as a quality check)
• Remember to test new questions/workflows in the Playground before Opus writes any automations.
• You can create your own "Claude x Jev" skill where you tell Opus how you personally want it to interact with Jev
• Note: You can run this in other models too. Fable, Codex, etc.
• Add an "uncertain" option to Jev's filtering process

Closing

I hope you've found this Opus 5.5 + Jev article valuable.

If you did, be sure to follow me here @aiedge_ - Every single week, I post breakdowns covering the hottest topics in AI.

If you enjoy written AI content, feel free to subscribe to my free newsletter.

My team and I send a weekly AI recap, one powerful AI workflow build & keep you up to speed on everything in the AI space.

100% free; read past publications here 👉 https://newsletter.aiedgehq.co/