Skip to content

Serverless Quickstart

Deploy a secure AI environment in under 2 minutes using the Lucid CLI. No infrastructure setup required.

Alpha Access Required

Lucid is in private alpha. Request access before proceeding.

Prerequisites

  • Python 3.12+
  • A Lucid alpha account

Step 1: Install the CLI

pip install lucid-clilucid --versionlucid-cli 0.1.0

Step 2: Authenticate

lucid loginEmail: [email protected]
Password:
Logged in as [email protected]

Or with flags for scripting:

lucid login -e [email protected]Logged in as [email protected]

Step 3: Browse the Catalog

See what's available to deploy:

lucid catalog modelsMODEL ID NAME PROVIDER CONTEXT TEE
meta-llama/Llama-3.1-8B-Instruct Llama 3.1 8B Instruct meta 128K Yes
meta-llama/Llama-3.1-70B-Instruct Llama 3.1 70B Instruct meta 128K Yes
Qwen/Qwen2.5-72B-Instruct Qwen 2.5 72B alibaba 128K Yes
microsoft/Phi-3.5-mini-instruct Phi 3.5 Mini microsoft 128K Yes
lucid catalog auditorsPROFILE NAME AUDITORS
coding Coding Profile injection, eval
chat Chat Profile injection, toxicity, sovereignty
workflow Workflow Profile injection, soc2
customer Customer Profile injection, toxicity, pii, soc2
default Default Profile injection

Step 4: Deploy

Deploy an environment with a single command:

lucid apply --model llama-3.1-8b --profile chat[*] Creating serverless environment...
[+] Environment created: env-abc123def456

Connection URL: https://env-abc123def456.serverless.lucid.ai
Model: meta-llama/Llama-3.1-8B-Instruct
Auditors: injection, toxicity, sovereignty
Region: us-east-1

[+] Environment ready! No infrastructure provisioning needed.

Your environment is now live at the connection URL.

Step 5: Verify TEE Attestation

Confirm your environment is running in a Trusted Execution Environment:

lucid verify environment env-abc123def456[*] Fetching routing info for environment env-abc123def456...
[+] Model: https://model-xyz.serverless.lucid.ai (us-east-1) - amd_sev_snp
[+] Auditor: https://auditor-abc.serverless.lucid.ai (us-east-1) - amd_sev_snp

[*] 2/2 endpoints have attestation reports

Deployment Options

Flag Description Example
--model <id> Model from catalog --model llama-3.1-70b
--profile <name> Auditor profile --profile coding
--region <code> Data residency --region eu

Example: Coding Assistant

lucid apply --model llama-3.1-70b --profile coding[+] Environment created: env-xyz789...
Connection URL: https://env-xyz789.serverless.lucid.ai
Model: meta-llama/Llama-3.1-70B-Instruct
Auditors: injection, eval

Example: EU Data Residency

lucid apply --model qwen-72b --profile workflow --region eu[+] Environment created: env-eu456...
Region: eu-west-1

Managing Your Environment

Check Status

lucid statusAgents (1):
NAME STATUS MODEL GPU
my-agent running meta-llama/Llama-3.1-8B A100

View Logs

lucid logs my-agent[2025-09-15 10:30:00] Agent started
[2025-09-15 10:30:01] Auditors initialized
[2025-09-15 10:30:05] Request processed: injection=pass, toxicity=pass

View AI Passports

lucid passport listID AGENT TIMESTAMP
pass-001 agent-abc123 2025-09-15T10:30:00Z
pass-002 agent-abc123 2025-09-15T10:31:00Z
lucid passport show pass-001Passport ID: pass-001
Hardware Attested: true
TEE Type: AMD SEV-SNP
Auditors: injection, toxicity, sovereignty

Next Steps