Question 1

What is the Tessera Optimize Layer?

Accepted Answer

The Tessera Optimize Layer is a thin proxy that lives in your LLM request path. Your application points its OpenAI, Anthropic, or Google client at Tessera; Tessera forwards each request to the provider but first applies four moves: auto-route to a cheaper model when quality holds on your golden-set eval, auto-cache identical requests at the edge, auto-compress prompts via LLMLingua-2 where safe, auto-batch where batch APIs apply. Every saved dollar is measured directly from proxy logs, not inferred from a billing CSV.

Question 2

How does Tessera measure savings?

Accepted Answer

Savings are measured from Tessera proxy logs at request granularity. For each request that gets routed, cached, compressed, or batched, Tessera records the counterfactual provider cost (what the request would have cost without the optimization) and the actual incurred cost. Aggregate Ongoing Savings equal the sum of (counterfactual minus actual) across all in-scope workloads in the period. Provider price moves and unrelated workload shrinkage are excluded; only optimizations attributable to Tessera enter the Performance Fee.

Question 3

How is Tessera different from Helicone, Portkey, or Langfuse?

Accepted Answer

Helicone, Portkey, and Langfuse are observability platforms — they trace requests and show dashboards. Tessera is an optimize layer — we sit in the request path and actively route, cache, compress, and batch on every call. We bill on measured savings from our own logs, not on a SaaS seat. You can keep your existing observability tool — Tessera imports their traces and reports back to them.

Question 4

What does the Pilot cost?

Accepted Answer

On the Annual tier, Tessera bills against a prepaid balance (Claude API style). You top up your account via Stripe Checkout (minimum $100) or invoice. Tessera debits 25% of every measured-savings dollar in real time. There is no floor, no retainer, and no separate Diagnostic phase. If your balance reaches zero, the proxy automatically pauses optimizations and forwards requests as passthrough — no fees accrue while paused. Top up to resume. Enterprise tier (for workloads above $500,000 per month in savings) bills via invoice on NET terms at 15% instead. Quality preservation guaranteed at 0.90 by canary; three-day breach triggers auto-disable plus a 10% fee credit applied to your balance.

Question 5

Does Tessera modify our production code?

Accepted Answer

No. Tessera is added to your request path via two HTTP headers and one config-line change — you point your OpenAI/Anthropic/Google client at the Tessera proxy base URL and add an API key. Tessera never modifies your application source, never deploys into your codebase, and never makes provider-side changes on your account. All optimization logic runs inside the Tessera proxy infrastructure. You can disable Tessera at any time by reverting the two headers, or by using the in-dashboard pause control (see next question).

Question 6

Can I pause Tessera at any time?

Accepted Answer

Yes. Every operator dashboard ships with an always-available kill-switch — account-wide and per-workload. When engaged, the Tessera proxy bypasses all four optimizations (route, cache, compress, batch) and forwards your requests to the upstream provider as pure passthrough. Performance Fee does not accrue on paused traffic. Pause is reversible at any time without notice. The pause right is contractually preserved in §8 of the Tessera Terms of Service — Tessera does not work uncontrolled in your stack.

Question 7

Who is Tessera for?

Accepted Answer

Two primary shapes carry most Annual signups: (1) Series A-B AI-native SaaS CTO, $20k-$200k per month on LLM APIs, gross margin under pressure, can change a base-URL in 30 minutes and signs up in 72 hours; (2) Series B-D scale-up adding AI features, $50k-$500k per month, AI Platform Lead owns the budget, light security review in 2-4 weeks. Workloads tagged regulated (HIPAA, PCI-DSS, SOC 2 in-scope) never auto-route — the compliance gate blocks routing at the code level. Above $500k/mo in measured savings, the Enterprise tier applies (15% rate, invoice billing, custom MSA).

Question 8

How does Tessera handle data privacy?

Accepted Answer

Confidential Information furnished to Tessera is stored primarily inside the European Economic Area (EEA) under Estonian operating jurisdiction. We do not require, request, or process Client end-user personal data, model prompts, or model completions in their full content form — only token-count and structural metadata. US-based AI provider sub-processors (Anthropic, OpenAI, Google) are engaged solely for Tessera-internal analysis under strict anonymisation conditions per the Data Processing Agreement.

Question 9

Does Tessera accept referral fees from AI providers?

Accepted Answer

No. Tessera receives no affiliate revenue, referral fees, kickbacks, sponsorships, advisory-board honoraria, or any other compensation from any AI provider, gateway vendor, or observability platform we recommend in the course of operating the proxy. Client fees are our only income. This is contractually binding under §10 of the Tessera Terms of Service (Vendor Neutrality) and breach permits Clients to terminate without penalty and withdraw their balance.

Request	Time	Model	Flag	Tokens	Cost	Saved
req_92Aj	14:02:18	gpt-4o → gpt-4o-mini	routed	1,240	$0.0019	$0.0143
req_92Ai	14:02:14	gpt-4o	cache-hit	—	$0.00	$0.0163
req_92Ah	14:02:11	gpt-4o	passthrough	980	$0.0151	—
req_92Ag	14:02:09	gpt-4o → gpt-4o-mini	routed	1,620	$0.0026	$0.0187
req_92Af	14:02:04	gpt-4o	cache-hit	—	$0.00	$0.0142
req_92Ae	14:01:58	claude-opus-4-7 → claude-sonnet-4-6	routed	2,240	$0.0181	$0.0612
req_92Ad	14:01:51	gpt-4o	passthrough	1,840	$0.0286	—
req_92Ac	14:01:47	gpt-4o → gpt-4o-mini	routed	720	$0.0011	$0.0082
req_92Ab	14:01:42	gpt-4o	cache-hit	—	$0.00	$0.0218
req_92Aa	14:01:38	gpt-4o	passthrough	1,180	$0.0184	—

Three of the seven tabs your operator dashboard ships with.

Recent requests

Ranked by $ savings × reversibility ÷ engineering days.

Route classification → gpt-4o-mini

Enable prompt cache · doc-sum system prompt

Batch nightly embeddings

Compress retrieval-augmented prompts (LLMLingua-2)

Every dollar traces to a pricing_catalog snapshot version.

Your real dashboard reads from your real traffic.