Populate your tech radar with scored technologies
Workflow: Evaluation
1. Describe the task
Prism can read recent external signals for a technology topic and turn them into a populated radar. It queries the signals pool (news, patents, research) and the web via Perplexity, extracts the distinct technologies, and creates a technology element for each. Each element lands on your radar, segmented and scored against your configured readiness scale.
Here, it scouts the topic of solid-state batteries and places the results on an existing radar.
Example prompt:
Scout recent signals on solid-state battery technology. Based on the findings, create at least 10 technology elements, rate their Complexity, TRL, and Impact, and segment them on the Solid-State Battery radar.
2. Give context
Required inputs
-
A technology topic to scout, named narrowly (e.g. "solid-state batteries," not "energy storage").
-
A radar view with an element type and a configured readiness scale (TRL, MRL, or your own).
3. What ITONICS AI creates
Prism creates 10 technology elements from signals from the last year, rated and segmented on the Solid-State Battery radar.
Example output:
| Technology | Segment | TRL | Impact | Complexity |
| SSB OEM Automotive Validation and Pilot Fleet Integration | Automotive | 7 | 5 | 3 |
| Roll-to-Roll Manufacturing for Solid-State Batteries | Production | 6 | 4 | 4 |
| Solid-State Battery Gigafactory Scale-Up | Production | 6 | 5 | 5 |
| Lithium Metal Anodes for Solid-State Batteries | Fuel Cells and Battery | 5 | 5 | 5 |
| High-Pressure Stack Engineering for SSB Manufacturing | Production | 5 | 3 | 5 |
| Silicon Anodes for Solid-State Batteries | Fuel Cells and Battery | 4 | 4 | 4 |
| Bipolar Solid-State Battery Cell Architecture | Fuel Cells and Battery | 4 | 4 | 4 |
| Anode-Less Solid-State Battery Architecture | Fuel Cells and Battery | 4 | 4 | 5 |
| Solid-State Batteries for Grid-Scale Energy Storage | Storage | 4 | 5 | 4 |
| Self-Healing Adaptive Interphase Engineering for SSBs | Smart Materials | 3 | 5 | 5 |
Prism's analysis determines that OEM Automotive Validation is the most mature entry (TRL 7), with Toyota, BYD, Nissan, and Honda in active pilot phases. Self-Healing Adaptive Interphase Engineering, the least mature (TRL 3), is flagged as the highest-risk, highest-reward technology to watch.
Follow-up prompts:
Example prompt:
Summarize why each technology sits in its current TRL band, citing the strongest signal for each.
Example prompt:
Add the three most-cited competing approaches you found but left off the radar, and say why you excluded them.
Example prompt:
Re-scout the same topic filtered to patents from the last 6 months and flag what changed.
