Your AI that
actually works
Chat naturally. Set objectives. Watch it manage your inbox, schedule meetings, run workflows — and prove every action it takes.
Chat like you would
with a teammate
No rigid commands. No query syntax. Just tell Sidekick what you need and it figures out the rest. It asks clarifying questions, estimates costs, and confirms before acting.
- Context-aware conversation threads
- Multi-step task decomposition
- Cost estimates before execution
- Confirmation prompts for risky actions
Set objectives,
not instructions
Tell Sidekick the outcome you want. It breaks it into steps, estimates resources, and executes. You see progress in real time and can intervene at any point.
Routines that run while you sleep
Schedule recurring objectives on daily, weekly, or monthly cadences. Sidekick runs them on time, every time — and reports results when you wake up.
Daily inbox triage
Archive noise, flag priorities, draft replies — before you open your laptop.
Weekly reports
Pull metrics from 5 tools, compile insights, deliver a formatted summary every Monday.
Monthly reconciliation
Cross-check invoices, flag discrepancies, and prepare the summary for finance review.
Reactive triggers
for live events
Sidekick watches for the events that matter: VIP emails, SLA breaches, budget alerts, failed deployments. When they fire, Sidekick responds instantly within your defined playbook.
Memory that
gets smarter
Sidekick remembers your preferences, past decisions, and working context across sessions. No re-explaining. No lost threads. It adapts to how you work.
Three modes. Your choice.
Dial Sidekick’s autonomy up or down per workspace. Switch any time — no restart needed.
Supervised
You approve everything
- Sidekick plans and proposes
- Nothing executes without your OK
- Ideal for onboarding and high-risk work
Guided
Routine is automatic
- Handles known patterns autonomously
- Flags anomalies for your review
- Most teams land here after a week
Autonomous
Full speed, full proof
- Operates within budget and scope
- Proof logged for every action
- For mature workflows with guardrails
Trust through constraints
Sidekick earns trust by working within the bounds you set. Approval workflows, budget caps, and scope limits — all configurable per workspace.
Scope limits
Define exactly what Sidekick can and can't do per workspace. Actions outside scope are blocked.
Budget controls
Set daily, weekly, or monthly caps. Sidekick pauses automatically when approaching limits.
Approval workflows
Require human sign-off for high-stakes actions. Configure thresholds by cost, risk, or action type.
Proof of every
single action
Every action generates an execution receipt: what happened, why it was allowed, what it cost, and what outcome it moved. Export for compliance or share with stakeholders.
Managed or bring your own
Start with LumenFlow’s managed inference — no API keys needed. When you’re ready, plug in your own keys for OpenAI, Anthropic, or any compatible provider.
Managed inference
Zero config. We handle model selection, scaling, and cost optimization. Pay per action, not per token.
- No API keys required
- Automatic model routing
- Transparent per-action pricing
Bring Your Own Key
Full control over model choice and spend. Use your existing enterprise agreements and volume discounts.
- OpenAI, Anthropic, or compatible
- Your keys, your data, your models
- Enterprise volume pricing intact
Meet your new
Sidekick
Start with a single task. Watch it work. See the proof. Graduate to routines and triggers when you’re ready.