Autonomous tool and account setup
Agents choose and configure the tools a job needs, including software without a prebuilt connector. They can use Google and Apple accounts and work across computers and phones.
Solid
Freemium
Solid provides AI agents with computers, accounts, and budgets to carry out business tasks across approved tools. Users describe the desired outcome and rules; agents handle setup, execution, verification, and reporting, with approvals where needed.
Solidとは？
Solid is an AI agent platform for delegating business tasks that span software, computers, accounts, and paid services. Users provide a goal, access, rules, and approval points in plain language. Solid's agents handle setup and execution, check the result, and report back with a usable output or a clear explanation of what needs human judgment.
The platform is intended for extended workflows rather than isolated chat responses. Agents can work across approved systems, build missing workflow pieces, recover from tool failures, and coordinate additional agents or tools when a job requires more than one capability. Users retain control through access permissions, budgets, and approval rules.
Solidでできること
Cross-system task execution
With approved access, agents carry work across connected systems and keep handoffs moving. They can also build a missing step when an existing integration does not cover the workflow.
Verification and reporting
Agents check their work, show what changed, identify exceptions, and return results such as hosted links, test results, reports, or proposed fixes.
Failure recovery and learning
When a tool or setup fails, agents can investigate the issue, repair it, and verify that the job runs again. They retain effective fixes and incorporate team corrections into later work.
Budgets, approvals, and spending visibility
Users set spending limits and approval rules for tools, services, and other purchases. Agents can explain the cost of a job, including AI usage, machines, and purchases.
Long-running and coordinated jobs
Agents can continue working after the user steps away, create additional Solid agents, or bring in agents such as Codex and Claude Code to divide a larger task.
利用シーン
“Build and operate web apps”
Describe an app idea in plain language and have agents build, launch, test, and help maintain it. Solid resources also describe hosting Claude Code projects and moving Lovable apps from preview toward production with testing and approved repairs.
“HubSpot data and workflow maintenance”
Give Solid a HubSpot task and the rules for handling exceptions. Agents can compare records, repair syncs, update workflows, fix reports, audit a portal, and build workflow tools across HubSpot and connected systems.
“Lead research and approved outreach”
Agents research accounts and contacts on LinkedIn against an ideal customer profile, show the evidence, draft outreach for approval, and then follow up, book qualified meetings, and update the CRM when authorized.
“AI product evaluation”
Agents build scenarios and success criteria, simulate users completing key tasks after a release or change, judge outcomes against expected behavior, and report what passed, failed, and why.
“Production and customer issue resolution”
For a production alert, an agent can investigate impact, reproduce the issue, write and test a fix, and open it for engineer approval before deployment. For support work, it can trace a stalled ticket across systems, apply allowed fixes, and record the customer resolution.
よくある質問
What does a user provide to start a Solid job?
The user describes the desired result in plain language and supplies the required access, operating rules, examples, and approval points. Solid recommends starting with a job whose result can be checked, such as a sales demo, researched lead list, or recurring report.
Do I need to configure every integration myself?
No. Solid says its agents can choose tools and handle setup, including software without a prebuilt connector. They work only with the access you approve and can explain what is blocking progress when human input is needed.
How do users control agent spending and actions?
Users set budgets and approval rules. Agent purchases, machines, and AI usage draw from the same account balance, and users can ask for a breakdown of a job's costs or see what remains active after the job ends.
What happens when an agent gets stuck?
The agent can investigate a failed tool or setup, make a repair, and verify recovery. If it still needs a person, it explains the blocker. Solid also describes retaining successful fixes and learning from team corrections.
Can Solid be used by teams or embedded in another product?
Yes. The Solid API is intended for deploying always-on agents inside a product. Enterprise offerings include workspace access, budgets, policies, approvals, and deployment on Solid Cloud, in a customer's VPC, or on-premises depending on setup.
クイック情報
- Product type
- AI agent platform for business task delegation
- Source domain
- solid.tech
- Supported device environments
- Linux servers, Windows and macOS computers, iPhones, and Android phones
- Account support
- Google and Apple accounts
- Pricing model
- Monthly credits cover AI usage, machines, and approved agent purchases; a trial is available
- Deployment options
- Solid Cloud; enterprise options include customer VPC or on-premises deployment depending on setup
Solidの代替品
Simular
www.simular.ai
Simular is an autonomous computer platform that uses AI agents to operate real computers and automate digital workflows. It serves individuals, builders, operators, and businesses that need to automate tasks across desktop applications and websites, including workflows that do not expose traditional APIs.
OneCLI
onecli.sh
OneCLI is an open-source platform for giving employees personal AI agents that can work across company tools. It provides isolated sandboxes, gateway-enforced policies, scoped credentials, approvals, and audit logs for team use.
apra-fleet
apra-labs.github.io
apra-fleet runs a fleet of AI agents across multiple machines and provider CLIs. It provides a common execution model for combining Claude, Codex, Copilot, Antigravity, and local models.
Kody
kody.codes
Kody is a software platform that gives connected AI agents shared memory, credentials, reusable packages, integrations, and scheduled execution. It helps developers carry work between agents such as Cursor, Claude, ChatGPT, and Codex without rebuilding the same automation each time.
Automat Workforce
runautomat.com
Automat Workforce provides Ace, an AI teammate with its own Mac, email, phone, and company account. It works through workplace tools such as Slack, Teams, Gmail, Microsoft 365, calendars, chat, phone, SMS, and iMessage to complete tasks and request human input when needed.
Xorviex
xorviex.ai
Xorviex is a workspace for delegating research, analysis, writing, and connected-app tasks to coordinated AI agents. You describe an objective in natural language; the agents plan the work, use available tools, and a separate Supervisor AI audits the result.