01
Policy-bounded localization
Apply only the country and application rules supplied by the user or a versioned policy record, with every transformation citing its rule ID.
Mistral CV workflow · Beta
Primary via OpenRouterBeta · connectivity verifiedThis beta workflow separates candidate facts, target evidence, and an explicit country-policy packet before it drafts a CV.
Requested workflow
No account or payment for the first Career DNA report. The original source file is discarded after extraction.
Direct answer
A useful Mistral CV workflow should not infer national hiring rules from a country name. Candidate evidence is one source, the job description is another, and an approved country-policy packet is a third. The model may apply supplied rules for terminology, section order, date format, page conventions, or excluded personal details, but absent rules remain absent rather than becoming plausible local advice.
Where this workflow helps
01
Apply only the country and application rules supplied by the user or a versioned policy record, with every transformation citing its rule ID.
02
Adjust headings and document terminology when the policy packet requires it without changing the candidate’s underlying experience.
03
Create separate application versions with a visible policy, target, and evidence history instead of overwriting one universal document.
Four controlled passes
Each pass has one job. Keeping them separate makes omissions, unsupported claims, and target decisions easier to inspect.
Try the working upload tool →Lock employers, roles, dates, education, credentials, projects, actions, tools, scope, and outcomes before localization.
Accept versioned user- or product-supplied rules for country, language, headings, dates, length, and personal-information boundaries.
Separate target requirements from policy rules and map each requirement to direct, transferable, missing, or unverified evidence.
Generate the CV, cite the evidence IDs and policy rule IDs behind each transformation, then flag anything that lacks either source.
Fictional transformation
Fictional energy-project example using an illustrative user-supplied policy. It is not legal advice, a country benchmark, or evidence of Mistral output quality.
Weak source line
“Worked on renewable energy projects and coordinated many stakeholders.”
Recovered evidence
Evidence-rich draft
Coordinated grid-connection work for 3 solar projects totaling 86 MW, aligning engineering, legal, and 5 local authorities to submit every connection package before its contractual deadline.
Verification: Confirm the project and authority counts, capacity total, meaning of coordination, submission record, and the policy rule governing the target CV’s terminology and date style.
Copyable prompt
This prompt is useful when you want to run the editorial pass yourself. Replace every bracketed field and inspect the review output before using the draft.
Act as a policy-bounded CV editor. Do not infer country-specific conventions, legal requirements, protected personal information, or recruiter preferences.
VERIFIED CAREER PROFILE
[Paste candidate evidence with stable IDs for employers, titles, dates, education, credentials, projects, actions, tools, scope, and outcomes.]
SUPPLIED COUNTRY POLICY
{
"policy_version": "",
"country_or_market": "",
"language": "",
"terminology_rules": [],
"section_rules": [],
"date_and_length_rules": [],
"personal_information_rules": [],
"unknown_rules": []
}
TARGET JOB
[Paste one job description with source IDs.]
TASK
1. Validate that every proposed localization change has a supplied policy rule ID.
2. Map target requirements to direct evidence, transferable evidence, missing evidence, and unverified hard requirements.
3. Draft the requested resume or CV using only verified candidate evidence and supplied policy rules.
4. Attach evidence IDs to every claim and policy rule IDs to every heading, terminology, ordering, date, length, or personal-information decision.
5. Return missing policy questions separately. Do not fill them using memory or general assumptions.
BOUNDARIES
- Do not invent or alter employers, titles, dates, credentials, projects, tools, scope, numbers, seniority, ownership, or outcomes.
- Do not claim that a credential transfers across countries unless the supplied policy explicitly says so.
- Do not add a photo, age, nationality, marital status, address, or other personal detail unless the candidate requests it and the supplied policy explicitly permits it.
- Do not describe the draft as legally compliant.
- Return POLICY_CHECK, TARGET_MAP, DRAFT, CLAIM_AUDIT, and POLICY_QUESTIONS as separate sections.
FINAL REVIEW
Remove any claim without candidate evidence and any localization decision without a policy rule. Preserve unresolved items outside the export-ready CV.What the model does not solve
01
Rules must come from the user or a maintained product policy. Missing guidance becomes a question, not a model-generated convention.
02
Changing language or format cannot establish licensing, degree equivalence, work authorization, or eligibility in another jurisdiction.
03
A country label is not sufficient reason to add a photo, age, nationality, address, or family information. Candidate intent and supplied policy must both be explicit.
Routing and fallback contract
mistralai/mistral-small-3.2-24b-instruct through OpenRouter is the primary route. OpenRouter is the gateway, not the model provider, and this is not an official Mistral product session or a direct Mistral AI API connection.
Requested workflow
Mistral
Primary execution model
mistralai/mistral-small-3.2-24b-instruct
Primary gateway
OpenRouter provider-specific routing
Primary privacy controls
AI text stages: ZDR required · data collection deny
Configured fallback
GLM · used only when the primary route cannot complete
A known provider Terms of Service restriction, payment or credit failure, rate limiting, timeout, upstream failure, or invalid structured output can move a stage to the configured GLM fallback. Session provenance records the execution gateway, returned model identity, and provider identity when reported. When GLM completes a stage, it is labeled as GLM rather than Mistral. OpenRouter ZDR and data-collection controls apply only to the OpenRouter primary route, not to the GLM fallback. The fallback and separate image or scanned-PDF OCR paths are described in the Privacy Policy.
Mistral resume FAQ
Yes, as a beta workflow. It requests mistralai/mistral-small-3.2-24b-instruct through OpenRouter and may use the disclosed GLM fallback. The route passed a minimal connectivity check but still needs broader policy-bounded CV fixture evaluation.
No. The workflow applies only user- or product-supplied versioned policy rules. If a heading, date, length, photo, or personal-information rule is absent, it asks a question or leaves the decision unchanged.
It requests mistralai/mistral-small-3.2-24b-instruct through OpenRouter under explicit routing and execution-provenance controls. It is not a Le Chat session or a direct Mistral API connection.
No. It creates a reviewable draft from supplied evidence and policy rules. Candidates should verify legal, licensing, immigration, and application requirements with authoritative sources.
No. My Best Resume is an independent product. Mistral and Le Chat are trademarks of their respective owner and are referenced only to identify the workflow.
Method and sources
This page documents the primary model route, configured GLM fallback, and evidence controls used by My Best Resume. It does not publish quality rankings, hiring claims, or provider comparisons. The same fictional fixture set is used for release-candidate review before routing changes reach production; candidates must still verify every generated claim.
Compare another workflow
The reliable way to create a resume with ChatGPT is to separate the work into four passes: extract only verified career facts, choose evidence relevant to one target job, draf…
Open ChatGPT →Compare another workflow
A useful Claude resume workflow treats the model as a constrained editor across a larger source record. First preserve the career timeline and non-negotiable facts. Then defin…
Open Claude →Compare another workflow
A useful Gemini resume workflow begins by structuring documents and notes into named fields: role, dates, actions, scope, tools, stakeholders, and outcomes. The target job is …
Open Gemini →Compare another workflow
A useful DeepSeek resume workflow starts with a fact ledger and an explicit output contract. Titles, dates, employers, tools, scope, and measured outcomes are locked first. Th…
Open DeepSeek →Compare another workflow
A responsible Grok resume workflow should not treat a model name as permission to improvise current market conditions. It should lock the candidate record, analyze only the su…
Open Grok →Compare another workflow
A useful Kimi resume maker workflow should use available context to preserve a long career record, not to blend it into one plausible story. Roles, projects, dates, locations,…
Open Kimi →Compare another workflow
A cross-language Qwen resume workflow should translate meaning while freezing facts. The source-language excerpt remains the authority for employers, titles, dates, credential…
Open Qwen →Start with evidence
Upload once, see the first Career DNA report for free, then choose the target and verify every generated claim.