Hire someone who ships with AI.

148 services from developers who build with coding agents. Fixed scopes, honest ranges, no discovery call to find out the price.

  • AI features

    Token budget and caching layer for your AI feature

    Cut your model spend with caching, routing and per-user budgets, without changing what your users experience.

    • Semantic and exact-match caching with a measured hit rate
    • Model routing sending easy requests to cheaper models
    • Per-user and per-tenant spend caps with graceful degradation

    From

    1,500

    4-8 days

    LiteLLMRedisNode.js
  • AI features

    Harden your LLM feature against prompt injection

    Close the gaps that let a crafted input make your agent leak data, call the wrong tool or ignore its instructions.

    • Threat model of your prompt, tool and data flows
    • Attack suite of injection attempts run against your live feature
    • Input and output guardrails with tool-call allowlisting

    From

    1,800

    5-9 days

    Claude APIPythonSemgrep
  • AI features

    MCP server so agents can use your internal tools

    Expose your internal APIs to coding and support agents safely, with scoped permissions and a full audit trail.

    • MCP server exposing your chosen tools with typed schemas
    • Authentication and per-tool permission scopes
    • Audit log of every tool call with arguments and caller identity

    From

    2,000

    5-10 days

    TypeScriptMCP SDKDocker
  • AI features

    Streaming chat UI with tool calls and real error states

    The front end your AI feature deserves: token streaming, cancellation, retries and messages that survive a refresh.

    • Streaming interface with stop, regenerate and edit-and-resend
    • Tool-call rendering showing what the model is doing while it runs
    • Persisted conversation history that survives reloads and reconnects

    From

    2,000

    6-10 days

    Vercel AI SDKNext.jsTypeScript
  • AI features

    Evaluation harness so prompt changes stop regressing

    A test suite for your AI feature that runs in CI and tells you when a prompt or model change makes things worse.

    • Golden dataset built from your real production traffic
    • Automated scoring combining assertions and model-graded rubrics
    • CI job that fails the build when scores drop below the baseline

    From

    2,200

    6-10 days

    PythonPromptfooGitHub Actions
  • AI features

    Make your RAG bot stop inventing answers

    Diagnose why retrieval misses, then fix chunking, reranking and prompting until answers are grounded and citable.

    • Retrieval diagnosis separating chunking, embedding and ranking failures
    • Reranking stage with measured precision improvement at rank five
    • Rewritten grounding prompt with mandatory citations and refusal path

    From

    2,200

    6-11 days

    Cohere RerankpgvectorPython
  • AI features

    Moderation for user-generated text and images

    Automatic screening of uploads and posts with tunable thresholds, an appeals path and a queue for the grey area.

    • Moderation pipeline covering text and image uploads
    • Configurable thresholds per policy category with an override list
    • Human review queue with keyboard-driven approve and reject

    From

    2,400

    7-12 days

    OpenAI APICloudflare WorkersPostgreSQL
  • AI features

    Meeting transcription with searchable summaries

    Calls transcribed with speaker labels, summarised into decisions and actions, and searchable across every past meeting.

    • Transcription pipeline with speaker diarisation and timestamps
    • Summaries structured into decisions, actions and open questions
    • Search across the full archive with jump-to-timestamp playback

    From

    2,500

    7-12 days

    DeepgramOpenAI APISupabase
  • AI features

    Replace keyword search with semantic search

    Search that understands intent, with hybrid ranking so exact matches still win when users type an exact term.

    • Embedding pipeline with incremental reindexing on content changes
    • Hybrid retrieval combining vector similarity and keyword matching
    • Relevance benchmark against your current search on fifty real queries

    From

    2,600

    7-12 days

    QdrantOpenAI APIFastAPI
  • AI features

    Agent that triages support before you wake up

    Incoming tickets classified, tagged, prioritised and drafted overnight so your morning starts with replies to approve.

    • Classification into your existing categories with confidence scores
    • Draft replies generated for the ticket types you approve for automation
    • Escalation rules for angry, legal or billing-sensitive messages

    From

    3,000

    8-15 days

    Claude APIn8nZendesk API
  • AI features

    Turn messy documents into structured data

    Contracts, CVs or reports converted into validated JSON you can query, with a review queue for low-confidence fields.

    • Typed extraction schema with validation rejecting malformed output
    • Per-field confidence scoring and a human review queue
    • Batch processing API with progress tracking for large uploads

    From

    3,200

    9-16 days

    Claude APIPydanticFastAPI
  • AI features

    RAG chatbot trained on your documentation

    A support assistant that answers from your docs, cites its sources and says it does not know when it does not.

    • Ingestion pipeline with chunking tuned to your document structure
    • Retrieval with citation links back to the source page
    • Refusal behaviour and confidence thresholds tested against a question set

    From

    3,500

    10-18 days

    pgvectorOpenAI APINext.js
  • AI features

    In-app copilot that walks new users through setup

    A contextual assistant that knows the user's account state and can complete setup steps for them, not just explain them.

    • Copilot with access to the current user's account context
    • Tool actions that perform setup steps with confirmation before writes
    • Deflection tracking showing which support questions it removes

    From

    3,500

    10-18 days

    Vercel AI SDKOpenAI APINext.js
  • AI features

    Recommendation engine built on embeddings, not rules

    Replace hand-written if-statements with similarity and behaviour signals, measured against your current click-through.

    • Content and behaviour embeddings with a scheduled refresh job
    • Ranking blending similarity, recency and popularity signals
    • Cold-start strategy for new items and new users

    From

    4,000

    12-20 days

    pgvectorOpenAI APIPython
  • AI features

    Natural-language questions over your product data

    Let your team ask questions in plain English and get charts backed by governed, read-only SQL they can inspect.

    • Semantic layer defining tables, joins and approved metrics
    • Query generation restricted to read-only views with row limits
    • Generated SQL shown alongside every answer for verification

    From

    4,200

    12-20 days

    OpenAI APIPostgreSQLdbt
  • AI features

    Contract comparison that flags what changed and why

    Upload two versions of an agreement and get a clause-level diff with risk commentary your legal team can act on.

    • Clause segmentation and alignment across document versions
    • Materiality scoring so cosmetic edits do not drown the real changes
    • Side-by-side review interface with export to annotated PDF

    From

    4,200

    12-20 days

    Claude APIPythonReact
  • AI features

    Fine-tuned small model to cut your inference bill

    Move a high-volume, narrow task off a frontier model onto a tuned small model at a fraction of the cost per call.

    • Training set assembled and cleaned from your production logs
    • Fine-tuned model with evaluation against the frontier-model baseline
    • Deployed inference endpoint with autoscaling and a cost-per-call figure

    From

    4,500

    12-20 days

    Hugging FacePyTorchModal
  • AI features

    Multi-agent workflow with human checkpoints

    A durable pipeline where specialised agents research, draft and review, pausing for your approval at the steps that matter.

    • Workflow graph with explicit state, retries and resumable runs
    • Human approval steps with a review interface and edit capability
    • Per-step tracing so you can see exactly why an output looked as it did

    From

    6,000

    16-28 days

    LangGraphClaude APITemporal
  • AI features

    Private LLM deployment for data you cannot send out

    An open-weight model running in your own environment, benchmarked on your tasks and sized to your real throughput.

    • Model selection benchmarked on your tasks against a hosted baseline
    • GPU-backed inference deployment with autoscaling and health checks
    • OpenAI-compatible endpoint so existing code needs minimal changes

    From

    6,000

    16-28 days

    vLLMLlama 3Kubernetes
  • AI features

    Voice agent that handles routine inbound calls

    A phone agent that answers, qualifies and books, then hands to a human the moment the conversation leaves its script.

    • Voice agent with interruption handling and natural turn-taking
    • Warm transfer to a human with the conversation context passed across
    • Call recordings, transcripts and outcomes written to your CRM

    From

    6,500

    18-30 days

    VapiTwilio APIOpenAI Realtime API
Marketplace — hire someone who ships with AI | FlowKy | FlowKy