In this guide
- Stan’s take: why we use JEV for decisions at scale
- The use cases and features that matter to us
- A practical play: qualify the market before enriching every person
- Confidence is useful, but it is not your accuracy rate
- Build an evaluation set that exposes your edge cases
- Current features, model versions and limits
- Jev pricing and a transparent cost model
- Jev versus rules, chat models and agents
- What implementation and handover should include
- Buyer questions
Stan’s take: why we use JEV for decisions at scale
We have used TypeSafe since launch. For the decision tasks we give it, JEV has been one of the fastest, most cost-efficient and dependable models in our stack. I like it when the job is to evaluate context and return a decision, especially company scoring and ICP validation.
In our own workflows, we have processed thousands of companies in minutes at a fraction of the cost of the more general models we previously used for those tasks. That is our reported experience, not a controlled benchmark or a guarantee for every workload. Input size, model choice and the decision itself affect both speed and cost.
The important part is the context. We supply the company information and a clear definition of fit, then ask for a focused decision. JEV is most useful when that answer can move the workflow forward without asking a general chat model to write an essay.
The use cases and features that matter to us
| Use case | Feature | Why we use it |
|---|---|---|
| Validate ICP fit | Context-based classification | Decide whether researched companies match a clearly defined market. |
| Prioritize accounts | Structured scoring decisions | Apply the same rubric across a large audience. |
| Route work to the right next step | Typed outputs | Let the workflow act on a defined result rather than parsing free-form prose. |
| Identify uncertain cases | Confidence information | Send borderline decisions for review after validating the threshold on your own examples. |
| Process a large research batch | Focused decision models | Evaluate throughput and cost on the narrow task instead of paying for unnecessary generation. |
Feature references: TypeSafe decision models; TypeSafe confidence guidance.
A practical play: qualify the market before enriching every person
Here is a practical way to apply that approach to your own team:
- Gather the company facts that explain its business model and target customers.
- Define the fit criteria and a small set of examples that show what should pass or fail.
- Use JEV to classify or score the companies, then review a sample and the uncertain cases.
- Spend contact-enrichment and outreach effort on the accepted accounts, and use reviewed exceptions to improve the rubric.
Confidence is useful, but it is not your accuracy rate
TypeSafe derives Choice and Score confidence from the distribution of model probabilities. A concentrated distribution produces higher confidence; an even spread produces lower confidence. That number is not the same as your observed percentage of correct decisions. The official confidence documentation recommends thresholds suited to the use case and consequences.
Choose thresholds with labeled examples. Run historical records through the proposed questions without changing live ownership. For each candidate threshold, calculate precision among automatically routed records, coverage of the total workload and the size of the review queue.
For example, suppose a hypothetical 200-record evaluation produces 120 automatic routes with 114 correct assignments. That is 95% precision at 60% coverage. It is an arithmetic example, not a Jev benchmark. The right decision depends on the cost of six misroutes versus reviewing the other 80 records.
Do not force all decisions through one threshold. Routing a message to a review queue is more reversible than suppressing a promising lead or initiating external outreach. Evaluate those actions separately. A low-confidence result should remain visible, not become an automatic rejection.
Build an evaluation set that exposes your edge cases
Include ordinary leads and the cases that create operational friction: mixed support and sales requests, consultants researching for a client, students, vague messages, personal email domains and multilingual submissions. Keep a holdout sample that was not used while refining the criteria.
Record disagreement between human reviewers before blaming the model. If both labels are defensible, revise the policy or provide a review path. Measure errors by category. High overall accuracy can hide a weak result for an important minority, such as existing customers seeking expansion.
Compare three baselines: the current manual process, simple rules and the Jev-assisted design. A rule based on explicit form selection may outperform a model where the needed information is already structured. Reserve model calls for decisions that need interpretation.
Current features, model versions and limits
Reviewed October 18, 2026. TypeSafe's model reference lists Jev 1.14 and 1.13, with default limits of 64k tokens per request and 32k per question. It also documents organization-level request and token rate limits. Model aliases can move, so record the returned version and pin a tested version where stable evaluation matters. See models and limits.
The October 14 release introduced experimental image, bounding-box and extended-context options under explicit flags. The vendor warns that these features have limitations for production use. Do not include them as assumed requirements in an initial lead-routing build. Start with supported text decisions and evaluate new capabilities separately. See the Jev 1.14 announcement.
When the API is unavailable or rate-limited, preserve the event and use a bounded retry or review queue. The operational system needs a fallback even if the model usually responds quickly. Latency should be measured across your complete data preparation and CRM path, not only the model call.
Jev pricing and a transparent cost model
As reviewed October 18, 2026, the official model rate is $42 per billion input tokens, equivalent to $0.042 per million, with output free. That is a token rate, not a flat price per lead. Use billed input usage and your selected access route to calculate actual cost. The official model reference is the pricing source.
For an illustrative estimate, 100,000 records averaging 1,000 billed input tokens each total 100 million tokens. At the stated rate, model input cost is $4.20. That excludes enrichment, workflow-platform charges, hosting, retries and human review. Measure total billed input rather than counting only the visible customer message.
At this unit price, taxonomy design and review effort may matter more than shaving a few tokens. Removing necessary evidence to reduce cost can increase misrouting and manual rework. Evaluate cost per correctly resolved record, including review, before presenting an ROI case.
Jev versus rules, chat models and agents
| Approach | Use when | Watch for |
|---|---|---|
| Deterministic rules | Inputs and policy are explicit | Unmaintained exceptions and overlapping conditions |
| Jev | A narrow interpretation must become a typed decision | Ambiguous criteria and unvalidated confidence thresholds |
| A text-generating model | The output needs prose, synthesis or explanation | Unsupported content and output handling |
| Hermes or another agent | The job requires gathering information and coordinating tools | Access scope, cost and unreviewed actions |
These components can work together. An agent can gather account evidence; Jev can classify it; a workflow platform can apply the approved routing policy. Keep each component's responsibility visible so an incorrect outcome can be traced to evidence, interpretation or execution.
What implementation and handover should include
Ask for a versioned taxonomy, labeled evaluation set, threshold report, field contract, integration, failure procedure and monitoring view. The team should know how to inspect a decision, override it and test a changed rubric before release. Discuss a Jev workflow with Stan. frontBrick implementation is scoped and priced around the business process, not the model's token bill.
Buyer questions
Can Jev write personalized outreach?
Its core role is returning structured decisions. Use it to classify relevance or route work, then use an appropriate writing tool and review process for prose.
Does typed output mean the answer is always correct?
No. A valid label can still be the wrong judgment. Evaluate business accuracy on your own records separately from whether the response has the expected structure.
What confidence threshold should we use?
There is no universal number. Select it from a labeled evaluation and the cost of mistakes. Measure both precision and review workload, then monitor changes after release.
Can Jev find missing account information?
The model evaluates supplied state. Fetch verified information through your research or enrichment layer, retain its provenance, and pass the relevant context into the decision.
Should we use the latest model alias?
It is convenient for exploration. For a production process with tuned criteria and thresholds, record the model version and evaluate changes before switching.
How do we prove it is better than our current process?
Compare it against current routing and simple rules on the same held-out records. Include misroutes, review time, unresolved cases and total cost, rather than only response speed.
