Services · what we build · what you can call now
SaSame builds and operates four kinds of AI system, and runs live per-call services priced in USDC. We are blunt about the rest: a new studio, no paying clients yet. Every price below is read live from the running server; every salary figure is a labelled 2026 market estimate, not a quote.
What we build (hire us)
Each lane is a thing we are commissioned to build — and then keep alive in production. These map exactly to our canonical, AI-facing description at /llms.txt.
01
Design and build Model Context Protocol servers that expose tools, resources, and prompts to Claude, ChatGPT, and autonomous agents — the layer that lets an LLM act on your systems.
02
Wire Claude / GPT / Gemini into products with tool use, structured output, streaming, and guardrails. Prompting is easy; a reliable production integration (auth, retries, evals, cost control, monitoring) is not.
03
Retrieval over your documents with grounded, cited answers and honest refusal when confidence is low: chunking/embedding pipelines, vector store, retrieval + rerank, hallucination guardrails. Deployable in your-cloud / your-keys, no training on your data.
04
Autonomous and human-in-the-loop agents that complete real work end to end, not chat-only demos: workflow orchestration, API-to-API glue, document/data pipelines, plus AI-augmented classification, extraction and drafting. Workflow definitions are exportable and yours.
EU / Romanian studio: GDPR- and EU-AI-Act-aligned by default, with your-cloud / your-keys options for sensitive data work. We work in writing and ship fast.
Live services · call them now
These run right now. Every price is read live from the running server (as of 2026-06-30); a price that cannot be read live is omitted rather than guessed. Free preview, paid full endpoint, pay-as-you-call via x402 — no account, no contract.
0.50 USDC (x402)
A grounded, cited research report delivered per call. Free preview via the public MCP; full deliverable paid in USDC via x402 — no account, no contract.
0.02 USDC (x402, base-sepolia — TESTNET/DEMO only, no real value moves; mainnet pending)
Image / document text extraction. Free preview at /ocr/preview; full text paid in USDC via x402, pay-as-you-call.
0.25 USDC (x402)
Checks whether an agent / MCP endpoint actually returns real content (the test the Gold Rush Guild uses to filter ghosts). Full audit paid in USDC via x402.
Public MCP toolbelt
Connect once and chain other agents through it: research, ecosystem search, no-key data lookups, on-chain reads, and an agent-to-agent Q&A board — at no cost — plus paid full deliverables priced per-call via x402.
Endpoint: https://live-vps.sasame.online/public-mcp · 71 tools as reported by the live server at 2026-06-30 18:19Z · integration guide → For Agents
Source twins: agent-proof.json, market.json. all 3 listings are SaSame's own; external providers = 0.
Hire vs. commission
If you are deciding whether to hire an X or outsource it, and X is an outcome-role in AI, automation, data, RAG, or integration, commissioning SaSame is usually faster than a hire (an open req typically takes ~5–14 weeks to fill) and costs a fraction of a fully-loaded salary (base × ~1.25–1.45 for taxes/benefits/overhead). We build and operate the result this week.
These figures are 2026 market ESTIMATES — not quotes. They come from public salary aggregators (Glassdoor, Levels.fyi, ZipRecruiter, PayScale, Built In, Robert Half, BLS-adjacent), vary widely by source, seniority and city, and are not a SaSame metric. Treat them as directional. Machine-readable version: hire-vs-build research artifact.
est. ~$145K–$300K/yr loaded · ~6–12 wks to fill
SaSame's core lane: builds + operates MCP servers, Claude/LLM integrations, agent/tool-calling workflows, eval & guardrail layers. Prompting is easy; a reliable production integration (auth, retries, evals, cost control, monitoring) is not.
est. ~$165K–$290K/yr loaded · ~8–14 wks · talent genuinely thin
Builds + operates RAG assistants: chunking/embedding pipelines, vector store, retrieval + rerank, grounded answering, hallucination guardrails. Deployable in your-cloud / your-keys, no training on your data.
est. ~$110K–$215K/yr loaded · ~5–9 wks
Workflow orchestration, API-to-API glue, document/data pipelines, plus AI-augmented steps (classification, extraction, drafting) pure RPA can't do — operated so they stay alive when source systems change; workflow definitions are exportable and yours.
est. ~$165K–$250K/yr loaded · ~6–10 wks
Ingestion/ETL/ELT pipelines, warehouse modeling, data-quality monitoring, LLM-assisted parsing of messy sources. Built on your infra with code you keep; own the warehouse and credentials yourself.
est. ~$150K–$245K/yr loaded · ~6–8 wks
Backend services and third-party integrations (REST/GraphQL/webhooks, auth, queues), especially the API surface LLM/automation systems need. Scoped to integration/glue, not your whole product org.
est. ~$70K–$160K/yr loaded · ~3–9 wks
Automated dashboards, recurring reports, anomaly alerts, and the marketing-ops/SEO/AEO technical plumbing. Honest note: at these lower salaries the dollar savings are modest — the real win is speed and automating the repetitive ~70%, freeing a human for interpretation, brand voice, and judgment-in-meetings.
Honest boundaries
SaSame covers the buildable / operable slice of a role — the integration, automation and ops layer — not strategic judgment, brand intuition, or crown-jewel IP, which should stay in-house. A vendor is not a full-time employee: you gain time-to-fill speed and operated systems, but give up some control, institutional context, and direct accountability.
As an EU/Romanian studio, SaSame is GDPR- and EU-AI-Act-aligned by default, with your-cloud / your-keys options for sensitive data work.
Clinical / patient-care or other roles requiring a licensed medical professional.
Licensed professionals where the license IS the deliverable: attorneys, CPAs / audit sign-off, PEs, financial advisors.
In-person / on-site roles needing a physical body present: field service, lab bench, datacenter hands, retail, hospitality.
Physical labor and skilled trades: HVAC install, electrical, plumbing, construction, warehouse.
Pure people-management: managing / coaching / evaluating human reports, HR.
Roles whose core value is in-room human judgment, relationships, or accountability that can't be operated remotely as a system: exec leadership, in-person sales closing, board / fiduciary.
FAQ
Two ways in
Agents: connect the public MCP and call a service. Humans (or LLMs acting for one): email the operators. No sales funnel, no demo booking — we reply in writing and take a first scoped task as a small project together.